Skip to main content

Advertisement

Springer Nature Link
Account
Menu
Find a journal Publish with us Track your research
Search
Cart
  1. Home
  2. Machine Intelligence Research
  3. Article

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

  • Review
  • Open access
  • Published: 27 September 2024
  • Volume 21, pages 1011–1061, (2024)
  • Cite this article

You have full access to this open access article

Download PDF
Machine Intelligence Research Aims and scope Submit manuscript
A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
Download PDF
  • Enyan Dai  ORCID: orcid.org/0000-0001-9715-02801,
  • Tianxiang Zhao1,
  • Huaisheng Zhu1,
  • Junjie Xu1,
  • Zhimeng Guo1,
  • Hui Liu2,
  • Jiliang Tang2 &
  • …
  • Suhang Wang  ORCID: orcid.org/0000-0003-3448-48781 

  • 5475 Accesses

  • 45 Citations

  • 2 Altmetric

  • Explore all metrics

Abstract

Graph neural networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trust-worthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users’ trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

Article PDF

Download to read the full article text

Similar content being viewed by others

Fair and Privacy-Preserving Graph Neural Network

Chapter © 2023

Exploring the Versatile Applications of Graph Neural Networks

Chapter © 2025

Graph neural networks: Historical backgrounds, present revolutions, and conventionalization for the future

Article 09 June 2025

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.
  • Computer Ethics
  • Data Privacy
  • Digital Ethics
  • Machine Learning
  • Meta-Ethics
  • Privacy
Use our pre-submission checklist

Avoid common mistakes on your manuscript.

References

  1. J. Kawahara, C. J. Brown, S. P. Miller, B. G. Booth, V. Chau, R. E. Grunau, J. G. Zwicker, G. Hamarneh. Brainnetcnn: Convolutional neural networks for brain networks; towards predicting neurodevelopment. NeuroImage, vol. 146, pp. 1038–1049, 2017. DOI: https://doi.org/10.1016/j.neuroimage.2016.09.046.

    Article  Google Scholar 

  2. J. N. Wang, S. Zhang, Y. H. Xiao, R. Song. A review on graph neural network methods in financial applications. Journal of Data Science, vol.20, no.2, pp. 111–134, 2022. DOI: https://doi.org/10.6339/22-JDS1047.

    Article  Google Scholar 

  3. W. L. Hamilton, R. Ying, J. Leskovec. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 1025–1035, 2017.

    Google Scholar 

  4. T. N. Kipf, M. Welling. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017.

    Google Scholar 

  5. J. Chen, T. F. Ma, C. Xiao. FastGCN: Fast learning with graph convolutional networks via importance sampling. In Proceedings of the 6th International Conference on Learning Representations, Vancouver, Canada, 2018.

    Google Scholar 

  6. T. Xiao, Z. Y. Chen, D. L. Wang, S. H. Wang. Learning how to propagate messages in graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 1894–1903, 2021. DOI: https://doi.org/10.1145/3447548.3467451.

    Chapter  Google Scholar 

  7. T. X. Zhao, X. Zhang, S. H. Wang. Exploring edge disentanglement for node classification. In Proceedings of ACM Web Conference 2022, ACM, Lyon, France, pp. 1028–1036, 2022. DOI: https://doi.org/10.1145/3485447.3511929.

    Chapter  Google Scholar 

  8. L. Lv, J. B. Cheng, N. B. Peng, M. Fan, D. B. Zhao, J. H. Zhang. Auto-encoder based graph convolutional networks for online financial anti-fraud. In Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering & Economics, IEEE, Shenzhen, China, 2019. DOI: https://doi.org/10.1109/CIFEr.2019.8759109.

    Google Scholar 

  9. M. Harl, S. Weinzierl, M. Stierle, M. Matzner. Explainable predictive business process monitoring using gated graph neural networks. Journal of Decision Systems, vol. 29, no. S1, pp. 312–327, 2020. DOI: https://doi.org/10.1080/12460125.2020.1780780.

    Article  Google Scholar 

  10. X. X. Li, Y. Zhou, N. Dvornek, M. H. Zhang, S. Y. Gao, J. T. Zhuang, D. Scheinost, L. H. Staib, P. Ventola, J. S. Duncan. BrainGNN: Interpretable brain graph neural network for fMRI analysis. Medical Image Analysis, vol. 74, Article number 102233, 2021. DOI: https://doi.org/10.1016/j.media.2021.102233.

  11. W. Q. Fan, Y. Ma, Q. Li, Y. He, E. Zhao, J. L. Tang, D. W. Yin. Graph neural networks for social recommendation. In Proceedings of World Wide Web Conference, ACM, San Francisco, USA, pp. 417–426, 2019. DOI: https://doi.org/10.1145/3308558.3313488.

    Chapter  Google Scholar 

  12. Q. Y. Tan, N. H. Liu, X. Hu. Deep representation learning for social network analysis. Frontiers in Big Data, vol. 2, Article number 2, 2019. DOI: https://doi.org/10.3389/fdata.2019.00002.

  13. J. Y. Chen, Z. Q. Shi, Y. Y. Wu, X. H. Xu, H. B. Zheng. Link prediction adversarial attack, [Online], Avaüable: https://arxiv.org/abs/1810.01110, 2018.

    Google Scholar 

  14. M. Jin, H. Chang, W. W. Zhu, S. Sojoudi. Power up! Robust graph convolutional network against evasion attacks based on graph powering, [Online], Available: https://arxiv.org/abs/1905.10029, 2019.

    Google Scholar 

  15. X. L. He, J. Y. Jia, M. Backes, N. Z. Gong, Y. Zhang. Stealing inks from graph neural networks. In Proceedings of the 30th USENIX Security Symposium, pp. 2669–2686, 2021.

    Google Scholar 

  16. Z. K. Zhang, M. Chen, M. Backes, Y. Shen, Y. Zhang. Inference attacks against graph neural networks. In Proceedings of the 31st USENIX Security Symposium, Boston, USA, pp. 4543–4560, 2022.

    Google Scholar 

  17. Y. W. Sun, S. H. Wang, X. F. Tang, T. Y. Hsieh, V. Honavar. Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach. In Proceedings of Web Conference 2020, ACM, Taipei, China, pp. 673–683, 2020. DOI: https://doi.org/10.1145/3366423.3380149.

    Chapter  Google Scholar 

  18. E. Y. Dai, S. H. Wang. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ACM, Israel, pp. 680–688, 2021. DOI: https://doi.org/10.1145/3437963.3441752.

    Chapter  Google Scholar 

  19. M. Buyl, T. De Bie. DeBayes: A Bayesian method for debiasing network embeddings. In Proceedings of the 37th International Conference on Machine Learning, pp. 1220–1229, 2020.

    Google Scholar 

  20. N. Smuha. Ethics Guidelines for Trustworthy AI. In AI & Ethics, Date: 2019/05/28-2019/05/28, Location: Brussels (Digityser), Belgium, 2019.

    Google Scholar 

  21. D. Solans, B. Biggio, C. Castillo. Poisoning attacks on algorithmic fairness. In Proceedings of European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, Ghent, Belgium, pp. 162–177, 2020. DOI: https://doi.org/10.1007/978-3-030-67658-210.

    Google Scholar 

  22. N. Mehrabi, M. Naveed, F. Morstatter, A. Galstyan. Exacerbating algorithmic bias through fairness attacks. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp.8930–8938, 2021. DOI: https://doi.org/10.1609/aaai.v35i10.17080.

    Google Scholar 

  23. W. Q. Fan, W. Jin, X. R. Liu, H. Xu, X. F. Tang, S. H. Wang, Q. Li, J. L. Tang, J. P Wang, C. Aggarwal. Jointly attacking graph neural network and its explanations, [Online], Available: https://arxiv.org/abs/2108.03388, 2021.

    Google Scholar 

  24. Y. Zhang, Y. Y. Zhao, Z. Q. Li, X. Q. Cheng, Y. Wang, O. Kotevska, P. S. Yu, T. Derr. A survey on privacy in graph neural networks: Attacks, preservation, and applications, [Online], Available: https://arxiv.org/abs/2308.16375, 2023.

    Google Scholar 

  25. A. Said, T. Derr, M. Shabbir, W. Abbas, X. Koutsoukos. A survey of graph unlearning, [Online], Available: https://arxiv.org/abs/2310.02164, 2023.

    Google Scholar 

  26. W. Jin, Y. X. Li, H. Xu, Y. Q. Wang, S. W. Ji, C. Aggarwal, J. L. Tang. Adversarial attacks and defenses on graphs: A review, a tool and empirical studies, [Online], Available: https://arxiv.org/abs/2003.00653, 2020.

    Google Scholar 

  27. Y. S. Dong, J. Ma, S. Wang, C. Chen, J. D. Li. Fairness in graph mining: A survey. IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 10, pp. 10583–10602, 2023. DOI: https://doi.org/10.1109/TKDE.2023.3265598.

    Article  Google Scholar 

  28. H. Yuan, H. Y. Yu, J. Wang, K. Li, S. W. Ji. On explainability of graph neural networks via subgraph explorations. In Proceedings of the 38th International Conference on Machine Learning, pp. 12241–12252, 2021.

    Google Scholar 

  29. H. Zhang, B. Wu, X. L. Yuan, S. R. Pan, H. H. Tong, J. Pei. Trustworthy graph neural networks: Aspects, methods, and trends. Proceedings of the IEEE, vol. 112, no. 2, pp. 97–139, 2024. DOI: https://doi.org/10.1109/JPROC.2024.3369017.

    Article  Google Scholar 

  30. H. J. Wu, C. Wang, Y. Tyshetskiy, A. Docherty, K. Lu, L. M. Zhu. Adversarial examples for graph data: Deep insights into attack and defense. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, pp. 4816–4823, 2019. DOI: https://doi.org/10.24963/ijcai.2019/669.

    Google Scholar 

  31. W. Jin, Y. Ma, X. R. Liu, X. F. Tang, S. H. Wang, J. L. Tang. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 66–74, 2020. DOI: https://doi.org/10.1145/3394486.3403049.

    Chapter  Google Scholar 

  32. E. Y. Dai, W. Jin, H. Liu, S. H. Wang. Towards robust graph neural networks for noisy graphs with sparse labels. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining, ACM, USA, pp. 181–191, 2022. DOI: https://doi.org/10.1145/3488560.3498408.

    Google Scholar 

  33. P. Y. Liao, H. Zhao, K. Y. L. Xu, T. Jaakkola, G. J. Gordon, S. Jegelka, R. Salakhutdinov. Information obfuscation of graph neural networks. In Proceedings of the 38th International Conference on Machine Learning, pp. 6600–6610, 2021.

    Google Scholar 

  34. C. H. Wu, F. Z. Wu, Y. Cao, Y. F. Huang, X. Xie. FedGNN: Federated graph neural network for privacy-preserving recommendation, [Online], Available: https://arxiv.org/abs/2102.04925, 2021.

    Google Scholar 

  35. R. Ying, D. Bourgeois, J. X. You, M. Zitnik, J. Leskovec. GNNExplainer: Generating explanations for graph neural networks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 829, 2019.

    Google Scholar 

  36. E. Y. Dai, S. H. Wang. Towards self-explainable graph neural network. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, ACM, Australia, pp. 302–311, 2021. DOI: https://doi.org/10.1145/3459637.3482306.

    Chapter  Google Scholar 

  37. L. C. Sun, J. Wang, P. S. Yu, B. Li. Adversarial attack and defense on graph data: A survey, [Online], Available: https://arxiv.org/abs/1812.10528, 2018.

    Google Scholar 

  38. B. Z. Wu, J. T. Li, C. B. Hou, G. J. Fu, Y. T. Bian, L. Chen, J. Z. Huang. Recent advances in reliable deep graph learning: Adversarial attack, inherent noise, and distribution shift, [Online], Available: https://arxiv.org/abs/2202.07114, 2022.

    Google Scholar 

  39. Y. Q. Zhu, W. Z. Xu, J. H. Zhang, Q. Liu, S. Wu, L. Wang. Deep graph structure learning for robust repres-entations: A survey, [Online], Available: https://arxiv.org/abs/2103.03036v1, 2021.

    Google Scholar 

  40. H. C. Liu, Y. Q. Wang, W. Q. Fan, X. R. Liu, Y. X. Li, S. Jain, Y. H. Liu, A. Jain, J. L. Tang. Trustworthy AI: A computational perspective. ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 1, Article number 4, 2023. DOI: https://doi.org/10.1145/3546872.

  41. J. Zhou, G. Q. Cui, S. D. Hu, Z. Y. Zhang, C. Yang, Z. Y. Liu, L. F. Wang, C. C. Li, M. S. Sun. Graph neural networks: A review of methods and applications. AI Open, vol. 1, pp. 57–81, 2020. DOI: https://doi.org/10.1016/j.aiopen.2021.01.001.

    Article  Google Scholar 

  42. T. X. Zhao, X. Zhang, S. H. Wang. Graphsmote: Imbalanced node classification on graphs with graph neural networks. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ACM, Israel, pp. 833–841, 2021. DOI: https://doi.org/10.1145/3437963.3441720.

    Chapter  Google Scholar 

  43. B. B. Xu, H. W. Shen, B. J. Sun, R. An, Q. Cao, X. Q. Cheng. Towards consumer loan fraud detection: Graph neural networks with role-constrained conditional random field. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 4537–4545, 2021. DOI: https://doi.org/10.1609/aaai.v35i5.16582.

    Google Scholar 

  44. F. Yang, K. J. Fan, D. D. Song, H. K. Lin. Graph-based prediction of protein-protein interactions with attributed signed graph embedding. BMC Bioinformatics, vol. 21, no. 1, Article number 323, 2020. DOI: https://doi.org/10.1186/s12859-020-03646-8.

  45. X. T. Zhang, H. Liu, Q. M. Li, X. M. Wu. Attributed graph clustering via adaptive graph convolution. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, pp. 4327–4333, 2019. DOI: https://doi.org/10.24963/ijcai.2019/601.

    Google Scholar 

  46. X. F. Wang, J. H. Li, L. Yang, H. M Mi. Unsupervised learning for community detection in attributed networks based on graph convolutional network. Neurocomputing, vol. 456, pp. 147–155, 2021. DOI: https://doi.org/10.1016/j.neucom.2021.05.058.

    Article  Google Scholar 

  47. D. Shchur, S. Günnemann. Overlapping community detection with graph neural networks, [Online], Available: https://arxiv.org/abs/1909.12201, 2019.

    Google Scholar 

  48. Z. D. Chen, X. Li, J. Bruna. Supervised community detection with line graph neural networks. In Proceedings of the 7th International Conference on Learning Representations, New Orleans, USA, 2019.

    Google Scholar 

  49. M. Girvan, M. E. J. Newman. Community structure in social and biological networks. Proceedings of the National Academy of Sciences of the United States of America, vol. 99, no. 12, pp. 7821–7826, 2002. DOI: https://doi.org/10.1073/pnas.122653799.

    Article  MathSciNet  Google Scholar 

  50. J. O. Garcia, A. Ashourvan, S. Muldoon, J. M. Vettel, D. S. Bassett. Applications of community detection techniques to brain graphs: Algorithmic considerations and implications for neural function. Proceedings of the IEEE, vol. 106, no. 5, pp. 846–867, 2018. DOI: https://doi.org/10.1109/JPROC.2017.2786710.

    Article  Google Scholar 

  51. A. Sankar, Y. Z. Liu, J. Yu, N. Shah. Graph neural networks for friend ranking in large-scale social platforms. In Proceedings of Web Conference 2021, ACM, Ljubljana, Slovenia, pp. 2535–2546, 2021. DOI: https://doi.org/10.1145/3442381.3450120.

    Chapter  Google Scholar 

  52. S. Arora. A survey on graph neural networks for knowledge graph completio, [Online], Available: https://arxiv.org/abs/2007.12374, 2020.

    Google Scholar 

  53. V. Duddu, A. Boutet, V. Shejwalkar. Quantifying privacy leakage in graph embedding. In Proceedings of the 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, ACM, Darmstadt, Germany, pp. 76–85, 2020. DOI: https://doi.org/10.1145/3448891.3448939.

    Google Scholar 

  54. I. E. Olatunji, W. Nejdl, M. Khosla. Membership inference attack on graph neural networks. In Proceedings of the 3rd IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, IEEE, Atlanta, USA, pp.11–20, 2021. DOI: https://doi.org/10.1109/TP-SISA52974.2021.00002.

    Google Scholar 

  55. X. L. He, R. Wen, Y. X. Wu, M. Backes, Y. Shen, Y. Zhang. Node-level membership inference attacks against graph neural networks, [Online], Available: https://arx-iv.org/abs/2102.05429, 2021.

    Google Scholar 

  56. B. Wu, X. W Yang, S. R. Pan, X. L. Yuan. Adapting membership inference attacks to GNN for graph classification: Approaches and implications. In Proceedings of IEEE International Conference on Data Mining, IEEE, Auckland, New Zealand, pp. 1421–1426, 2021. DOI: https://doi.org/10.1109/ICDM51629.2021.00182.

    Google Scholar 

  57. Z. X. Zhang, Q. Liu, Z. Y. Huang, H. Wang, C. Q. Lu, C. R. Liu, E. H. Chen. GraphMI: Extracting private graph data from graph neural networks. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, Montreal, Canada, pp. 3749–3755, 2021. DOI: https://doi.org/10.24963/ijcai.2021/516.

    Google Scholar 

  58. B. Wu, X. W. Yang, S. R. Pan, X. L. Yuan. Model extraction attacks on graph neural networks: Taxonomy and realization, [Online], Available: https://arxiv.org/abs/2010.12751, 2020.

    Google Scholar 

  59. Y. Shen, X. L. He, Y. F. Han, Y. Zhang. Model stealing attacks against inductive graph neural networks. In Proceedings of IEEE Symposium on Security and Privacy, IEEE, San Francisco, USA, pp. 1175–1192, 2022. DOI: https://doi.org/10.1109/SP46214.2022.9833607.

    Google Scholar 

  60. Y. Li, B Y. Qian, X. L Zhang, H. Liu. Graph neural network-based diagnosis prediction. Big Data, vol. 8, no. 5, pp. 379–390, 2020. DOI: https://doi.org/10.1089/big.2020.0070.

    Article  Google Scholar 

  61. Y. H. Long, M. Wu, Y. Liu, Y. Fang, C. K. Kwoh, J. M. Chen, J. W. Luo, X. L. Li. Pre-training graph neural networks for link prediction in biomedical networks. Bioinformatics, vol. 38, no. 8, pp. 2254–2262, 2022. DOI: https://doi.org/10.1093/bioinformatics/btac100.

    Article  Google Scholar 

  62. M. Rigaki, S. Garcia. A survey of privacy attacks in machine learning. ACM Computing Surveys, vol. 56, no. 4, pp. 101, 2023. DOI: https://doi.org/10.1145/3624010.

    Google Scholar 

  63. M. Al-Rubaie, J. M. Chang. Privacy-preserving machine learning: Threats and solutions. IEEE Security & Privacy, vol. 17, no. 2, pp. 49–58, 2019. DOI: https://doi.org/10.1109/MSEC.2018.2888775.

    Article  Google Scholar 

  64. P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, R. G. L. D’Oliveira, H. Eichner, S. El Rouayheb, D. Evans, J. Gardner, Z. Garrett, A. Gascón, B. Ghazi, P. B. Gibbons, M. Gruteser, Z. Harchaoui, C. Y. He, L. He, Z. Y. Huo, B. Hutchinson, J. Hsu, M. Jaggi, T. Javidi, G. Joshi, M. Khodak, J. Konečný, A. Korolova, F. Koushanfar, S. Koyejo, T. Lepoint, Y. Liu, P. Mittal, M. Mohri, R. Nock, A. Özgür, R. Pagh, M. Raykova, H. Qi, D. Ramage, R. Raskar, D. Song, W. K. Song, S. U. Stich, Z. T. Sun, A. T. Suresh, F. Tramèr, P. Vepakomma, J. Y. Wang, L. Xiong, Z. Xu, Q. Yang, F. X. Yu, H. Yu, S. Zhao. Advances and open problems in federated learning, [Online], Available: https://arxiv.org/abs/1912.04977, 2019.

    Google Scholar 

  65. Z. L. Ji, Z. C. Lipton, C. Elkan. Differential privacy and machine learning: a survey and review, [Online], Available: https://arxiv.org/abs/1412.7584, 2014.

    Google Scholar 

  66. M. M. Yang, L. J. Lyu, J. Zhao, T. Q. Zhu, K. Y. Lam. Local differential privacy and its applications: A comprehensive survey, [Online], Available: https://arxiv.org/abs/2008.03686, 2020.

    Google Scholar 

  67. X. C. Niu, B. F. Li, C. L. Li, R. Xiao, H. C. Sun, H. B. Deng, Z. Z. Chen. A dual heterogeneous graph attention network to improve long-tail performance for shop search in e-commerce. In Proceedings of the 26th ACM SIGK-DD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 3405–3415, 2020. DOI: https://doi.org/10.1145/3394486.3403393.

    Google Scholar 

  68. Y. Rong, Y. T Bian, T. Y. Xu, W. Y. Xie, Y. Wei, W. B. Huang, J. Z. Huang. Self-supervised graph transformer on large-scale molecular data. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1053, 2020.

    Google Scholar 

  69. R. Shokri, M. Stronati, C. Z. Song, V. Shmatikov. Membership inference attacks against machine learning models. In Proceedings of IEEE Symposium on Security and Privacy, IEEE, Sein Jose, USA, pp. 3–18, 2017. DOI: https://doi.org/10.1109/SP.2017.41.

    Google Scholar 

  70. M. A. Rahman, T. Rahman, R. Laganière, N. Mohammed, Y. Wang. Membership inference attack against differentially private deep learning model. Transactions on Data Privacy, vol. 11, no. 1, pp. 61–79, 2018

    Google Scholar 

  71. B. Jayaraman, D. Evans. Evaluating differentially private machine learning in practice. In Proceedings of the 28th USENIX Security Symposium, Santa Clara, USA, pp. 1895–1912, 2019.

    Google Scholar 

  72. Y. Chen, L. F. Wu, M. Zaki. Iterative deep graph learning for graph neural networks: Better and robust node embeddings. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1620, 2020.

    Google Scholar 

  73. I. E. Olatunji, T. Funke, M. Khosla. Releasing graph neural networks with differential privacy guarantees, [Online], Available: https://arxiv.org/abs/2109.08907, 2021.

    Google Scholar 

  74. S. Sajadmanesh, D. Gatica-Perez. Locally private graph neural networks. In Proceedings of ACM SIGSAC Conference on Computer and Communications Security, ACM, pp. 2130–2145, 2021. DOI: https://doi.org/10.1145/3460120.3484565.

    Google Scholar 

  75. D. P. Xu, S. H. Yuan, X. T. Wu, H. Phan. DPNE: Differentially private network embedding. In Proceedings of the 22nd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Springer, Melbourne, Australia, pp. 235–246, 2018. DOI: https://doi.org/10.1007/978-3-319-93037-419.

    Chapter  Google Scholar 

  76. S. J. Zhang, H. Z. Yin, T. Chen, Z. Huang, L. Z. Cui, X. L. Zhang. Graph embedding for recommendation against attribute inference attacks. In Proceedings of Web Conference 2021, ACM, Ljubljana, Slovenia, pp. 3002–3014, 2021. DOI: https://doi.org/10.1145/3442381.3449813.

    Chapter  Google Scholar 

  77. C. Y. He, E. Ceyani, K. Balasubramanian, M. Annavaram, S. Avestimehr. SpreadGNN: Serverless multi-task federated learning for graph neural networks, [Online], Available: https://arxiv.org/abs/2106.02743, 2021.

    Google Scholar 

  78. Y. Pei, R. X. Mao, Y. Liu, C. R. Chen, S. F. Xu, F. Qiang, Blue Elephant Tech. Decentralized federated graph neural networks. In Proceedings of International Workshop on Federated and Transfer Learning for Data Sparsity and Confidentiality in Conjunction with IJCAI, 2021.

    Google Scholar 

  79. H. Xie, J. Ma, L. Xiong, C. Yang. Federated graph classification over non-IID graphs. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Vancouver, Canada, pp. 18839–18852, 2021.

    Google Scholar 

  80. B. H. Wang, A. Li, H. Li, Y. R. Chen. GraphFL: A federated learning framework for semi-supervised node classification on graphs, [Online], Available: https://arxiv.org/abs/2012.04187, 2020.

    Google Scholar 

  81. L. F. Zheng, J. Zhou, C. C. Chen, B. Z. Wu, L. Wang, B. Y. Zhang. ASFGNN: Automated separated-federated graph neural network. Peer-to-Peer Networking and Applications, vol. 14, no. 3, pp. 1692–1704, 2021. DOI: https://doi.org/10.1007/s12083-021-01074-w.

    Article  Google Scholar 

  82. J. Zhou, C. C. Chen, L. F. Zheng, H. W. Wu, J. Wu, X. L. Zheng, B. Z. Wu, Z. Q. Liu, L. Wang. Vertically federated graph neural network for privacy-preserving node classification, [Online], Available: https://arxiv.org/abs/2005.11903, 2020.

    Google Scholar 

  83. Z W Liu, L W Yang, Z W Fan, H Peng, P S Yu Federated social recommendation with graph neural network. ACM Transactions on Intelligent Systems and Technolog, vol. 13, no. 4, Article number 55, 2022. DOI: https://doi.org/10.1145/3501815.

  84. M. Chen, Z. K. Zhang, T. H. Wang, M. Backes, M. Humbert, Y. Zhang. Graph unlearning. In Proceedings of ACM SIGSAC Conference on Computer and Communications Security, ACM, Los Angeles, USA, pp. 499–513, 2022. DOI: https://doi.org/10.1145/3548606.3559352.

    Google Scholar 

  85. K. Wu, J. Shen, Y. Ning, T. Wang, W. H. Wang. Certified edge unlearning for graph neural networks. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Long Beach, USA, pp. 2606–2617, 2023. DOI: https://doi.org/10.1145/3580305.3599271.

    Chapter  Google Scholar 

  86. J. C. Wu, Y. Yang, Y. C. Qian, Y. D. Sui, X. Wang, X. N. He. Gif: A general graph unlearning strategy via influence function. In Proceedings of ACM Web Conference 2023, ACM, Austin, USA, pp. 651–661, 2023. DOI: https://doi.org/10.1145/3543507.3583521.

    Chapter  Google Scholar 

  87. E. Chien, C. Pan, O. Milenkovic. Efficient model updates for approximate unlearning of graph-structured data. In Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda, 2022.

    Google Scholar 

  88. K. Y. Li, G. C. Luo, Y. Ye, W. Li, S. H. Ji, Z. P. Cai. Adversarial privacy-preserving graph embedding against inference attack. IEEE Internet of Things Journal, vol.8, no. 8, pp. 6904–6915, 2021. DOI: https://doi.org/10.1109/JIOT.2020.3036583.

    Article  Google Scholar 

  89. B. H. Wang, J. Y. Guo, A. Li, Y. R. Chen, H. Li. Privacy-preserving representation learning on graphs: A mutual information perspective. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 1667–1676, 2021. DOI: https://doi.org/10.1145/3447548.3467273.

    Chapter  Google Scholar 

  90. J. Xu, S. Koffas, O. Ersoy, S. Picek. Watermarking graph neural networks based on backdoor attacks. In Proceedings of the 8th IEEE European Symposium on Security and Privacy, IEEE, Detft, Nethlalnrids, pp.1179–1197, 2023. DOI: https://doi.org/10.1109/EuroSP57164.2023.00072.

    Google Scholar 

  91. X. Y. Zhao, H. Z. Wu, X. P. Zhang. Watermarking graph neural networks by random graphs. In Proceedings of the 9th International Symposium on Digital Forensics and Security, IEEE, Elanig, Turkey, 2021. DOI: https://doi.org/10.1109/ISD-FS52919.2021.9486352.

    Google Scholar 

  92. A. Waheed, V. Duddu, N. Asokan. GrOVe: Ownership verification of graph neural networks using embeddings, [Online], Available: https://arxiv.org/abs/2304.08566, 2023.

    Google Scholar 

  93. E. Y. Dai, L. M. Cui, Z. Y. Wang, X. F. Tang, Y. H. Wang, M. Cheng, B. Yin, S. H. Wang. A unified framework of graph information bottleneck for robustness and membership privacy. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Long Beach, USA, pp. 368–379, 2023. DOI: https://doi.org/10.1145/3580305.3599248.

    Chapter  Google Scholar 

  94. C. Dwork, F. McSherry, K Nissim, A. Smith. Calibrating noise to sensitivity in private data analysis. In Proceedings of the 3rd Theory of Cryptography Conference, Springer, New York, USA, pp. 265–284, 2006. DOI: https://doi.org/10.1007/11681878_14.

    Chapter  Google Scholar 

  95. C. Dwork, A. Roth. The algorithmic foundations of differential privacy. Foundations and Trends® in Theoretical Computer Science, vol. 9, no. 3–4, pp. 211–407, 2014. DOI: https://doi.org/10.1561/0400000042.

    MathSciNet  Google Scholar 

  96. M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, L. Zhang. Deep learning with differential privacy. In Proceedings of ACM SIGSAC Conference on Computer and Communications Security, ACM, Vienna, Austria, pp. 308–318, 2016. DOI: https://doi.org/10.1145/2976749.2978318.

    Google Scholar 

  97. P. C. M. Arachchige, P. Bertok, I. Khalil, D. X. Liu, S. Camtepe, M. Atiquzzaman. Local differential privacy for deep learning. IEEE Internet of Things Journal, vol. 7, no. 7, pp. 5827–5842, 2020. DOI: https://doi.org/10.1109/JIOT.2019.2952146.

    Article  Google Scholar 

  98. N. Papernot, M. Abadi, Ú. Erlingsson, I. Goodfellow, K Talwar. Semi-supervised knowledge transfer for deep learning from private training data In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017

    Google Scholar 

  99. S Zhang, W W Ni Graph embedding matrix sharing with differential privacy. IEEE Access, vol.7, pp.89390–89399, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2927365.

    Article  Google Scholar 

  100. S. P. Kasiviswanathan, H. K. Lee, K. Nissim, S. Raskhodnikova, A Smith. What can we learn privately? SIAM Journal on Computing, vol. 40, no. 3, pp. 793–826, 2011. DOI: https://doi.org/10.1137/090756090.

    Article  MathSciNet  Google Scholar 

  101. J. Konečný, H. B. McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, D. Bacon. Federated learning: Strategies for improving communication efficiency, [Online], Available: https://arxiv.org/abs/1610.05492, 2016.

    Google Scholar 

  102. B. McMahan, E. Moore, D. Ramage, S. Hampson, B. A. Y. Arcas. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial intelligence and statistics, Fort Lauderdale, USA, pp. 1273–1282, 2017.

    Google Scholar 

  103. Q. Yang, Y. Liu, T. J. Chen, Y. X. Tong. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, vol.10, no. 2, Article number 12, 2019. DOI: https://doi.org/10.1145/3298981.

  104. L. Bourtoule, V. Chandrasekaran, C. A. Choquette-Choo, H. R. Jia, A. Travers, B. W. Zhang, D. Lie, N. Papernot. Machine unlearning. In Proceedings of IEEE Symposium on Security and Privacy, IEEE, San Francisco, USA, pp. 141–159, 2021. DOI: https://doi.org/10.1109/SP40001.2021.00019.

    Google Scholar 

  105. C. Guo, T. Goldstein, A. Hannun, L. Van Der Maaten. Certified data removal from machine learning models. In Proceedings of the 37th International Conference on Machine Learning, pp. 3832–3842, 2020.

    Google Scholar 

  106. J. Z. Qiu, Q. B. Chen, Y. X. Dong, J. Zhang, H. X. Yang, M. Ding, K. S. Wang. J. Tang. GCC: Graph contrastive coding for graph neural network pre-training. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 1150–1160, 2020. DOI: https://doi.org/10.1145/3394486.3403168.

    Chapter  Google Scholar 

  107. Y. C. Sun, T. P. Liu, P. H. Hu, Q. Liao, S. L. Ji, N. H. Yu, D. K. Guo, L. Liu. Deep intellectual property: A survey, [Online], Available: https://arxiv.org/abs/2304.14613, 2023.

    Google Scholar 

  108. P. Sen, G. Namata, M. Bilgic, L. Getoor, B. Gallagher, T. Eliassi-Rad. Collective classification in network data. AI magazine, vol.29, no.3, pp.93–106, 2003. DOI: https://doi.org/10.1609/aimag.v29i3.2157.

    Article  Google Scholar 

  109. S R Pan, J Wu, X Q Zhu, C Q Zhang, Y Wang Triparty deep network representation. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, USA, pp. 1895–1901, 2016.

    Google Scholar 

  110. J. McAuley, J. Leskovec. Learning to discover social circles in ego networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, pp. 539–547, 2012.

    Google Scholar 

  111. J. McAuley, J. Leskovec. Image labeling on a network: Using social-network metadata for image classification. In Proceedings of the 12th European Conference on Computer Vision, Springer, Florence, Italy, pp. 828–841, 2012. DOI: https://doi.org/10.1007/978-3-642-33765-9_59.

    Google Scholar 

  112. D. Shchur, M. Mumme, A. Bojchevski, S. Günnemann. Pitfalls of graph neural network evaluation, [Online], Available: https://arxiv.org/abs/1811.05868, 2018.

    Google Scholar 

  113. X. Wang, H. Y. Ji, C. Shi, B. Wang, Y. F. Ye, P. Cui, P. S. Yu. Heterogeneous graph attention network. In Proceedings of World Wide Web Conference, ACM, San Francisco, USA, pp. 2022–2032, 2019. DOI: https://doi.org/10.1145/3308558.3313562.

    Chapter  Google Scholar 

  114. C. Morris, N. M. Kriege, F. Bause, K. Kersting, P. Mutzel, M. Neumann. TUDataset: A collection of benchmark datasets for learning with graphs, [Online], Available: https://arxiv.org/abs/2007.08663, v1 2020.

    Google Scholar 

  115. K. D. Xu, H. G. Chen, S. J. Liu, P. Y. Chen, T. W. Weng, M. Y. Hong, X. Lin. Topology attack and defense for graph neural networks: An optimization perspective. In Proceedings of the 23th International Joint Conference on Artificial Intelligence, Macao, China, pp. 3961–3967, 2019. DOI: https://doi.org/10.24963/ijcai.2019/550.

    Google Scholar 

  116. J. Y. Chen, Y. Y. Wu, X. H. Xu, Y. X. Chen, H. B. Zheng, Q. Xuan. Fast gradient attack on network embedding, [Online], Available: https://arxiv.org/abs/1809.02797, 2018.

    Google Scholar 

  117. H. J. Dai, H. Li, T. Tian, X. Huang, L. Wang, J. Zhu, L. Song. Adversarial attack on graph structured data. In Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, pp. 1115–1124, 2018.

    Google Scholar 

  118. S. Geisler, T. Schmidt, H. Şirin, D. Zügner, A. Bojchevski, S. Günnemann. Robustness of graph neural networks at scale. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Vancouver, Canada, pp. 7637–7649, 2021.

    Google Scholar 

  119. Y. Ma, S. H. Wang, T. Derr, L. F. Wu, J. L. Tang. Graph adversarial attack via rewiring. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 1161–1169, 2021. DOI: https://doi.org/10.1145/3447548.3467416.

    Chapter  Google Scholar 

  120. D. Zügner, A. Akbarnejad, S. Günnemann. Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, London, UK, pp. 2847–2856, 2018. DOI: https://doi.org/10.1145/3219819.3220078.

    Chapter  Google Scholar 

  121. D. Zügner, S. Günnemann. Adversarial attacks on graph neural networks via meta learning. In Proceedings of the 7th International Conference on Learning Representations, New Drleans, USA, 2019.

    Google Scholar 

  122. J. H. Wang, M. N. Luo, F. Suya, J. D. Li, Z. J. Yang, Q. H. Zheng. Scalable attack on graph data by injecting vicious nodsl. Data Mining and Knowledge Discovery, vol. 34, no. 5, pp. 1363–1389, 2020. DOI: https://doi.org/10.1007/s10618-020-00696-7.

    Article  MathSciNet  Google Scholar 

  123. A. Bojchevski, S. Günnemann. Advesaarial attacks on node embeddings via graph poisoning. In Proceedings of the 36th International Conference on Machine Learning, Long Beach, USA, pp. 695–704, 2019.

    Google Scholar 

  124. H. Chang, Y. Rong, T. Y. Xu, W. B. Huang, H. L. Zhang, P. Cui, W. W. Zhu, J. Z. Huang. A restricted black-box adversarial framework towards attacking graph embedding models. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, AAAI, New York, USA, pp. 3389–3396, 2020. DOI: https://doi.org/10.1609/aaai.v34i04.5741

    Google Scholar 

  125. S. C. Tao, Q. Cao, H. W. Shen, J. J. Huang, Y. F. Wu, X. Q. Cheng. Single node injection attack against graph neural networks. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, ACM, Queensland, pp. 1794–1803, 2021. DOI: https://doi.org/10.1145/3459637.3482393.

    Chapter  Google Scholar 

  126. J. Q. Ma, S. R. Ding, Q. Z. Mei. Towards more practical adversarial attacks on graph neural networks. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 399, 2020.

    Google Scholar 

  127. Z. H. Xi, R. Pang, S. L. Ji, T. Wang. Graph backdoor. In Proceedings of the 30th USENIX Security Symposium, pp. 1523–1540, 2021.

    Google Scholar 

  128. Z. X. Zhang, J. Y. Jia, B. H. Wang, N. Z. Gong. Backdoor attacks to graph neural networks. In Proceedings of the 26th ACM Symposium on Access Control Models and Technologies, ACM, Spain, pp. 15–26, 2021. DOI: https://doi.org/10.1145/3450569.3463560.

    Chapter  Google Scholar 

  129. J. T. Li, T. Xie, L. Chen, F. F. Xie, X. N. He, Z. B. Zheng. Adversarial attack on large scale graph. IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 1, pp. 82–95, 2023. DOI: https://doi.org/10.1109/TKDE.2021.3078755.

    Google Scholar 

  130. Z. N. Hu, Y. X. Dong, K. S. Wang, K. W. Chang, Y. Z. Sun. GPT-GNN: Generative pre-training of graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 1857–1867, 2020. DOI: https://doi.org/10.1145/3394486.3403237.

    Chapter  Google Scholar 

  131. D. Ahmedt-Aristizabal, M. A. Armin, S. Denman, C. Fookes, L. Petersson. Graph-based deep learning for medical diagnosis and analysis: Past, present and future. Sensors, vol. 21, no. 14, Article number 4758, 2021. DOI: https://doi.org/10.3390/s21144758.

  132. W. H. Hu, B. W. Liu, J. Gomes, M. Zitnik, P. Liang, V. Pande, J. Leskovec. Strategies for pre-training graph neural networks. In Proceedings of the 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, 2020.

    Google Scholar 

  133. L. Chen, J. T. Li, J. Y. Peng, T. Xie, Z. X. Cao, K. Xu, X. N. He, Z. B Zheng. A survey of adversarial learning on graphs, [Online], Available: https://arxiv.org/abs/2003.05730, 2020.

    Google Scholar 

  134. F. Mujkanovic, S. Geisler, S. Günnemann, A. Bojchevski. Are defenses for graph neural networks robust? In Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 651, 2022.

    Google Scholar 

  135. E. Y. Dai, M. H. Lin, X. Zhang, S. H. Wang. Unnoticeable backdoor attacks on graph neural networks. In Proceedings of ACM Web Conference 2023, ACM, Austin, USA, pp. 2263–2273, 2023. DOI: https://doi.org/10.1145/3543507.3583392.

    Chapter  Google Scholar 

  136. X. Zou, Q. K. Zheng, Y. X. Dong, X. Y. Guan, E. Kharlamov, J. L. Lu, J. Tang. TDGIA: Effective injection attacks on graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 2461–2471, 2021. DOI: https://doi.org/10.1145/3447548.3467314.

    Chapter  Google Scholar 

  137. Y. Q. Chen, H. Yang, Y. G. Zhang, K. L. Ma, T. L. Liu, B. Han, J. Cheng. Understanding and improving graph injection attack by promoting unnoticeability. In Proceedings of the 10th International Conference on Learning Representations, 2022.

    Google Scholar 

  138. J. Xu, R. Wang, S. Koffas, K. T. Liang, S. Picek. More is better (mostly): On the backdoor attacks in federated graph neural networks. In Proceedings of the 38th Annual Computer Security Applications Conference, ACM, Austin, USA, pp. 684–698, 2022. DOI: https://doi.org/10.1145/3564625.3567999.

    Chapter  Google Scholar 

  139. I. J. Goodfellow, J. Shlens, C. Szegedy. Explaining and harnessing adversarial examples. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2015. DOI: https://doi.org/10.48550/arXiv.1412.6572.

    Google Scholar 

  140. Q. Y. Dai, X Shen, L. Zhang, Q. Li, D. Wang. Adversarial training methods for network embedding. In Proceedings of World Wide Web Conference, ACM, San Francisco, USA, pp. 329–339, 2019. DOI: https://doi.org/10.1145/3308558.3313445.

    Chapter  Google Scholar 

  141. Z. J. Deng, Y. P. Dong, J. Zhu. Batch virtual adversarial training for graph convolutional networks. AI Open, vol. 4, pp. 73–79, 2023. DOI: https://doi.org/10.1016/j.aiopen.2023.08.007.

    Article  Google Scholar 

  142. F. L. Feng, X. N. He, J. Tang, T. S. Chua. Graph adversarial training: Dynamically regularizing based on graph structure. IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 6, pp. 2493–3504, 2021. DOI: https://doi.org/10.1109/TKDE.2019.2957786.

    Article  Google Scholar 

  143. J. H. Wang, M. N. Luo, J. D. Li, Z. Q. Liu, J. Zhou, Q. H. Zheng. Robust unsupervised graph representation learning via mutual information maximization, [Online], Available: https://arxiv.org/abs/2201.08557, 2022.

    Google Scholar 

  144. L. Gosch, S. Geisler, D. Sturm, B. Charpentier, D. Zügner, S. Günnemann. Adversarial training for graph neural networks, [Online], Available: https://arxiv.org/abs/2306.15427v1, 2023.

    Google Scholar 

  145. J. Y. Chen, Y. Y. Wu, X. Lin, Q. Xuan. Can adversarial network attack be defended? [Online], Available: https://arxiv.org/abs/1903.05994, 2019.

    Google Scholar 

  146. X. Y. Wang, X. Q. Liu, C. J. Hsieh. GraphDefense: Towards robust graph convolutional networks, [Online], Available: https://arxiv.org/abs/1911.04429, 2019.

    Google Scholar 

  147. D. Zügner, S. Günnemann. Certifiable robustness and robust training for graph convolutional networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, Anchorage, USA, pp. 246–256, 2019. DOI: https://doi.org/10.1145/3292500.3330905.

    Chapter  Google Scholar 

  148. B. H. Wang, J. Y. Jia, X. Y. Cao, N. Z. Gong. Certified robustness of graph neural networks against adversarial structural perturbation. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 1645–1653, 2021. DOI: https://doi.org/10.1145/3447548.3467295.

    Chapter  Google Scholar 

  149. H. W. Jin, Z. Shi, A. Peruri, X. H. Zhang. Certified robustness of graph convolution networks for graph classification under topological attacks. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 709, 2020.

    Google Scholar 

  150. D. Zügner, S. Günnemann. Certifiable robustness of graph convolutional networks under structure perturbations. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 1656–1665, 2020. DOI: https://doi.org/10.1145/3394486.3403217.

    Chapter  Google Scholar 

  151. A. Bojchevski, S. Günnemann. Certifiable robustness to graph perturbations. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 747, 2019.

    Google Scholar 

  152. J. Klicpera, A. Bojchevski, S. Günnemann. Predict then propagate: Graph neural networks meet personalized pagerank. In Proceedings of the 7th International Conference on Learning Representations, New Orleans, USA, 2019.

    Google Scholar 

  153. Y. Scholten, J. Schuchardt, S. Geisler, A. Bojchevski, S. Günnemann. Randomized message-interception smoothing: Gray-box certificates for graph neural networks. In Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 2402, 2022.

    Google Scholar 

  154. N. Entezari, S. A. Al-Sayouri, A. Darvishzadeh, E. E. Papalexakis. All you need is low (rank): Defending against adversarial attacks on graphs. In Proceedings of the 13th International Conference on Web Search and Data Mining, ACM, Houston, USA, pp. 169–177, 2020. DOI: https://doi.org/10.1145/3336191.3371789.

    Chapter  Google Scholar 

  155. D. S. Luo, W. Cheng, W. C. Yu, B. Zong, J. C. Ni, H. F. Chen, X. Zhang. Learning to drop: Robust graph neural network via topological denoising. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ACM, Israel, pp. 779–787, 2021. DOI: https://doi.org/10.1145/3437963.3441734.

    Chapter  Google Scholar 

  156. L. Wang, W. C. Yu, W. Wang, W. Cheng, W. Zhang, H. Y. Zha, X. F. He, H. F. Chen. Learning robust representations with graph denoising policy network. In Proceedings of IEEE International Conference on Data Mining, IEEE, Beijing, China, pp. 1378–1383, 2019. DOI: https://doi.org/10.1109/ICDM.2019.00177.

    Google Scholar 

  157. X. F. Tang, Y. D. Li, Y. W. Sun, H. X. Yao, P. Mitra, S. H. Wang. Transferring robustness for graph neural network against poisoning attacks. In Proceedings of the 13th International Conference on Web Search and Data Mining, ACM, Houston, USA, pp. 600–608, 2020. DOI: https://doi.org/10.1145/3336191.3371851.

    Chapter  Google Scholar 

  158. X. Zhang, M. Zitnik. GNNGUARD: Defending graph neural networks against adversarial attacks. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 777, 2020.

    Google Scholar 

  159. D. Y. Zhu, Z. W. Zhang, P. Cui, W. W. Zhu. Robust graph convolutional networks against adversarial attacks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, Anchorage, USA, pp. 1399–1407, 2019. DOI: https://doi.org/10.1145/3292500.3330851.

    Chapter  Google Scholar 

  160. L. Chen, J. T. Li, Q. B. Peng, Y. Liu, Z. B. Zheng, C. Yang. Understanding structural vulnerability in graph convolutional networks. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, Canada, pp. 2249–2255, 2021. DOI: https://doi.org/10.24963/ijcai.2021/310.

    Google Scholar 

  161. D. Kim, A. Oh. How to find your friendly neighborhood: Graph attention design with self-supervision. In Proceedings of the 9th International Conference on Learning Representations, Austria, 2021.

    Google Scholar 

  162. Y. N. You, T. L. Chen, Y. D. Sui, T. Chen, Z. Y. Wang, Y. Shen. Graph contrastive learning with augmentations. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 488, 2020.

    Google Scholar 

  163. W. Jin, T. Derr, Y. Q. Wang, Y. Ma, Z. T. Liu, J. L. Tang. Node similarity preserving graph convolutional networks. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ACM, Israel, pp. 148–156, 2021. DOI: https://doi.org/10.1145/3437963.3441735.

    Chapter  Google Scholar 

  164. J. Y. Guo, S. Y. Li, Y. Zhao, Y. Zhang. Learning robust representation through graph adversarial contrastive learning. In Proceedings of the 27th International Conference on Database Systems for Advanced Applications, Springer, pp. 682–697, 2022. DOI: https://doi.org/10.1007/978-3-031-00123-9_54.

    Chapter  Google Scholar 

  165. S. Y. Feng, B. Y. Jing, Y. D. Zhu, H. H. Tong. Adversarial graph contrastive learning with information regularization. In Proceedings of ACM Web Conference 2022, ACM, pp. 1362–1371, 2022. DOI: https://doi.org/10.1145/3485447.3512183.

    Chapter  Google Scholar 

  166. L. Lin, J. H. Chen, H. N. Wang. Spectral augmentation for self-supervised learning on graphs. In Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda, 2023.

    Google Scholar 

  167. H. T. Tang, G. X. Ma, Y. R. Chen, L. Guo, W. Wang, B. Zeng, L. Zhan. Adversarial attack on hierarchical graph pooling neural networks, [Online], Available: https://arxiv.org/abs/2005.11560, 2020.

    Google Scholar 

  168. H. T. Zhang, T. H. Zheng, J. Gao, C. L. Miao, L. Su, Y. L. Li, K. Ren. Data poisoning attack against knowledge graph embedding. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, pp. 4853–4859, 2019. DOI: https://doi.org/10.24963/ijcai.2019/674.

    Google Scholar 

  169. H. W. Wang, F. Z. Zhang, X. Xie, M. Y. Guo. DKN: Deep knowledge-aware network for news recommendation. In Proceedings of World Wide Web Conference, International World Wide Web Conferences Steering Committee, Lyon, France, pp. 1835–1844, 2018. DOI: https://doi.org/10.1145/3178876.3186175.

    Google Scholar 

  170. C. H. Deng, X. Y. Li, Z. Feng, Z. R. Zhang. GARNET: Reduced-rank topology learning for robust and scalable graph neural networks. In Proceedings of the 1st Learning on Graphs Conference, Article number 3, 2022.

  171. M. M. Zhang, X. Wang, M. Q. Zhu, C. Shi, Z. Q. Zhang, J. Zhou. Robust heterogeneous graph neural networks against adversarial attacks. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI, pp. 4363–4370, 2022. DOI: https://doi.org/10.1609/aaai.v36i4.20357.

    Google Scholar 

  172. M. M. Zhang, L. M. Hu, C. Shi, X. Wang. Adversarial label-flipping attack and defense for graph neural networks. In Proceedings of IEEE International Conference on Data Mining, IEEE, Sorrento, Italy, pp. 791–800, 2020. DOI: https://doi.org/10.1109/ICDM50108.2020.00088.

    Google Scholar 

  173. Y. Y. Li, J. Yin, L. Chen. Unified robust training for graph neural networks against label noise. In Proceedings of the 25th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Springer, pp. 528–540, 2021. DOI: https://doi.org/10.1007/978-3-030-75762-5_42.

    Chapter  Google Scholar 

  174. E. Y. Dai, C. Aggarwal, S. H. Wang. NRGNN: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 227–236, 2021. DOI: https://doi.org/10.1145/3447548.3467364.

    Chapter  Google Scholar 

  175. T. Rahman, B. Surma, M. Backes, Y. Zhang. Fairwalk: Towards fair graph embedding. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, pp. 3289–3295, 2019. DOI: https://doi.org/10.24963/ijcai.2019/456.

    Google Scholar 

  176. A. A. Stoica, C. Riederer, A. Chaintreau. Algorithmic glass ceiling in social networks: The effects of social recommendations on network diversity. In Proceedings of World Wide Web Conference, International World Wide Web Conferences Steering Committee, Lyon, France, pp. 923–932, 2018. DOI: https://doi.org/10.1145/3178876.3186140.

    Google Scholar 

  177. N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, A. Galstyan. A survey on bias and fairness in machine learning. ACM Computing Surveys, vol. 54, no. 6, Article number 115, 2021. DOI: https://doi.org/10.1145/3457607.

  178. A. Olteanu, C. Castillo, F. Diaz, E. Kiciman. Social data: Biases, methodological pitfalls, and ethical boundaries. Frontiers in Big Data, vol. 2, Article number 13, 2019. DOI: https://doi.org/10.3389/fdata.2019.00013.

  179. H. Suresh, J. V. Guttag. A framework for understanding unintended consequences of machine learning, [Online], Available: https://arxiv.org/abs/1901.10002, 2019.

    Google Scholar 

  180. Y. S. Dong, N. H. Liu, B. Jalaian, J. D. Li. EDITS: Modeling and mitigating data bias for graph neural networks. In Proceedings of ACM Web Conference 2022, ACM, pp. 1259–1269, 2022. DOI: https://doi.org/10.1145/3485447.3512173.

    Chapter  Google Scholar 

  181. Y. X. Dong, O. Lizardo, N. V. Chawla. Do the young live in a “smaller world” than the old? Age-specific degrees of separation in a large-scale mobile communication network, [Online], Available: https://arxiv.org/abs/1606.07556, 2016.

    Google Scholar 

  182. X. F. Tang, H. X. Yao, Y. W. Sun, Y. Q. Wang, J. L. Tang, C. Aggarwal, P. Mitra, S. H. Wang. Investigating and mitigating degree-related biases in graph convoltuional networks. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, ACM, Ireland, pp. 1435–1444, 2020. DOI: https://doi.org/10.1145/3340531.3411872.

    Chapter  Google Scholar 

  183. C. Dwork, M. Hardt, T. Pitassi, O. Reingold, R. Zemel. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ACM, Cambridge, USA, pp. 214–226, 2012. DOI: https://doi.org/10.1145/2090236.2090255.

    Chapter  Google Scholar 

  184. F. Locatello, G. Abbati, T. Rainforth, S. Bauer, B. Schölkopf, O. Bachem. On the fairness of disentangled representations. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1309, 2019.

    Google Scholar 

  185. M. Hardt, E. Price, N. Srebro. Equality of opportunity in supervised learning. In Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 3323–3331, 2016.

    Google Scholar 

  186. P. Z. Li, Y. F. Wang, H. Zhao, P. Y. Hong, H. F. Liu. On dyadic fairness: Exploring and mitigating bias in graph connections. In Proceedings of the 9th International Conference on Learning Representations, Austria, 2021.

    Google Scholar 

  187. M. Kusner, J. Loftus, C. Russell, R. Silva. Counterfactual fairness. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 4069–4079, 2017.

    Google Scholar 

  188. J. Kang, J. R. He, R. Maciejewski, H. H. Tong. InFoRM: Individual fairness on graph mining. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 379–389, 2020. DOI: https://doi.org/10.1145/3394486.3403080.

    Chapter  Google Scholar 

  189. C. Agarwal, H. Lakkaraju, M. Zitnik. Towards a unified framework for fair and stable graph representation learning. un Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence, pp. 2114–2124, 2021.

    Google Scholar 

  190. I. Spinelli, S. Scardapane, A. Hussain, A. Uncini. Biased edge dropout for enhancing fairness in graph representation learning, [Online], Available: https://arxiv.org/abs/2104.14210v1, 2021.

    Google Scholar 

  191. A. Bose, W. Hamilton. Compositional fairness constraints for graph embeddings. In Proceedings of the 36th International Conference on Machine Learning, Long Beach, USA, pp. 715–724, 2019.

    Google Scholar 

  192. F. Masrour, T. Wilson, H. Yan, P. N. Tan, A. Esfahanian. Bursting the filter bubble: Fairness-aware network link prediction. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, AAAI, New York, USA, pp. 841–848, 2020. DOI: https://doi.org/10.1609/aaai.v34i01.5429.

    Google Scholar 

  193. N. Wang, L. Lin, J. D. Li, H. N. Wang. Unbiased graph embedding with biased graph observations. In Proceedings of ACM Web Conference 2022, ACM, Lyon, France, pp. 1423–1433, 2022. DOI: https://doi.org/10.1145/3485447.3512189.

    Chapter  Google Scholar 

  194. Y. S. Dong, J. Kang, H. H. Tong, J. D. Li. Individual fairness for graph neural networks: A ranking based approach. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 300–310, 2021. DOI: https://doi.org/10.1145/3447548.3467266.

    Chapter  Google Scholar 

  195. Ö. D. Köse, Y. N. Shen. Fairness-aware node representation learning, [Online], Available: https://arxiv.org/abs/2106.05391, 2021.

    Google Scholar 

  196. A. Khajehnejad, M. Khajehnejad, M. Babaei, K. P. Gummadi, A. Weller, B. Mirzasoleiman. CrossWalk: Fairness-enhanced node representation learning. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI, pp. 11963–11970, 2022. DOI: https://doi.org/10.1609/aaai.v36i11.21454.

    Google Scholar 

  197. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio. Generative adversarial nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Cambridge, USA, pp. 2672–2680, 2014.

    Google Scholar 

  198. A. Beutel, J. L. Chen, Z. Zhao, E. H. Chi. Data decisions and theoretical implications when adversarially learning fair representations, [Online], Available: https://arxiv.org/abs/1707.00075, 2017.

    Google Scholar 

  199. H. Edwards, A. Storkey. Censoring representations with an adversary. In Proceedings of the 4th International Conference on Learning Representations, San Juan, Puerto Rico, 2016. DOI: https://doi.org/10.48550/arXiv.1511.05897.

    Google Scholar 

  200. J. C. Liao, C. Huang, P. Kairouz, L. Sankar. Learning generative adversarial representations (GAP) under fairness and censoring constraints, [Online], Available: https://arxiv.org/abs/1910.00411, 2019.

    Google Scholar 

  201. D. Madras, E. Creager, T. Pitassi, R. Zemel. Learning adversarially fair and transferable representations. In Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, pp. 3384–3393, 2018.

    Google Scholar 

  202. M. Arjovsky, S. Chintala, L. Bottou. Wasserstein generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, pp. 214–223, 2017.

    Google Scholar 

  203. Z. M. Guo, T. Xiao, C. Aggarwal, H. Liu, S. H. Wang. Counterfactual learning on graphs: A survey, [Online], Available: https://arxiv.org/abs/2304.01391, 2023.

    Google Scholar 

  204. H. S. Zhu, G. J. Fu, Z. M. Guo, Z. W. Zhang, T. Xiao, S. H. Wang. Fairness-aware message passing for graph neural networks, [Online], Available: https://arxiv.org/abs/2306.11132, 2023.

    Google Scholar 

  205. T. N. Kipf, M. Welling. Variational graph auto-encoders, [Online], Available: https://arxiv.org/abs/1611.07308, 2016.

    Google Scholar 

  206. Z. M. Guo, J. L. Li, T. Xiao, Y. Ma, S. H. Wang. Towards fair graph neural networks via graph counterfactual. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, ACM, Birmingham, UK, pp. 669–678, 2023. DOI: https://doi.org/10.1145/3583780.3615092.

    Chapter  Google Scholar 

  207. Y. Wang, Y. Y. Zhao, Y. S. Dong, H. Y. Chen, J. D. Li, T. Derr. Improving fairness in graph neural networks via mitigating sensitive attribute leakage. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Washington DC, USA, pp. 1938–1948, 2022. DOI: https://doi.org/10.1145/3534678.3539404.

    Chapter  Google Scholar 

  208. O. D. Kose, Y. N. Shen. Demystifying and mitigating bias for node representation learning. IEEE Transactions on Neural Networks and Learning Systems, [Online], Available: https://ieeexplore.ieee.org/abstract/document/10103678. 2023.

    Google Scholar 

  209. H. Y. Ling, Z. M. Jiang, Y. Z. Luo, S. W. Ji, N. Zou. Learning fair graph representations via automated data augmentations. In Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda, 2023.

    Google Scholar 

  210. Y. S. Dong, S. Wang, Y. Wang, T. Derr, J. D. Li. On structural explanation of bias in graph neural networks. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Washington DC, USA, pp. 316–326, 2022. DOI: https://doi.org/10.1145/3534678.3539319.

    Chapter  Google Scholar 

  211. Y. S. Dong, S. Wang, J. Ma, N. H. Liu, J. D. Li. Interpreting unfairness in graph neural networks via training node attribution. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI, Washington DC, USA, pp. 7441–7449, 2023. DOI: https://doi.org/10.1609/aaai.v37i6.25905.

    Google Scholar 

  212. J. Ma, R. C. Guo, M. T. Wan, L. Q. Yang, A. D. Zhang, J. D. Li. Learning fair node representations with graph counterfactual fairness. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining, ACM, USA, pp. 695–703, 2022. DOI: https://doi.org/10.1145/3488560.3498391.

    Google Scholar 

  213. J. Palowitch, B. Perozzi. MONET: Debiasing graph embeddings via the metadata-orthogonal training unit, [Online], Available: https://arxiv.org/abs/1909.11793, 2019.

    Google Scholar 

  214. A. Asuncion, D. Newman. UCI machine learning repository, 2007.

    Google Scholar 

  215. K. L. Jordan, T. L. Freiburger. The effect of race/ethnicity on sentencing: Examining sentence type, jail length, and prison length. Journal of Ethnicity in Criminal Justice, vol. 13, no. 3, pp. 179–196, 2015. DOI: https://doi.org/10.1080/15377938.2014.984045.

    Article  Google Scholar 

  216. F. M. Harper, J. A. Konstan. The movielens datasets: History and context. ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, Article number 19, 2015. DOI: https://doi.org/10.1145/2827872.

  217. L. A. Adamic, N. Glance. The political blogosphere and the 2004 U.S. election: Divided they blog. In Proceedings of the 3rd International Workshop on Link Discovery, ACM, Chicago, USA, pp. 36–43, 2005. DOI: https://doi.org/10.1145/1134271.1134277.

    Chapter  Google Scholar 

  218. M. Babaei, P. Grabowicz, I. Valera, K. P. Gummadi, M. Gomez-Rodriguez. On the efficiency of the information networks in social media. In Proceedings of the 9th ACM International Conference on Web Search and Data Mining, ACM, San Francisco, USA, pp. 83–92, 2016. DOI: https://doi.org/10.1145/2835776.2835826.

    Google Scholar 

  219. M. Cha, H. Haddadi, F. Benevenuto, P. K. Gummadi. Measuring user influence in twitter: The million follower fallacy. In Proceedings of the 4th International Conference on Weblogs and Social Media, AAAI Press, Washington DC, USA, 2010. DOI: https://doi.org/10.1609/icwsm.v4i1.14033.

    Google Scholar 

  220. E. Y. Dai, J. Chen. Graph-augmented normalizing flows for anomaly detection of multiple time series. In Proceedings of the 10th International Conference on Learning Representations, 2022.

    Google Scholar 

  221. T. A. B. Snijders, G. G. Van de Bunt, C. E. G. Steglich. Introduction to stochastic actor-based models for network dynamics. Social Networks, vol. 32, no. 1, pp. 44–60, 2010. DOI: https://doi.org/10.1016/j.socnet.2009.02.004.

    Article  Google Scholar 

  222. R. Ying, R. N. He, K. F. Chen, P. Eksombatchai, W. L. Hamilton, J. Leskovec. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, London, UK, pp. 974–983, 2018. DOI: https://doi.org/10.1145/3219819.3219890.

    Chapter  Google Scholar 

  223. T. Liang, G. X. Zeng, Q. W. Zhong, J. F. Chi, J. H. Feng, X. Ao, J. Y. Tang. Credit risk and limits forecasting in E-commerce consumer lending service via multi-view-aware mixture-of-experts nets. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ACM, Israel, pp. 229–237, 2021. DOI: https://doi.org/10.1145/3437963.3441743.

    Chapter  Google Scholar 

  224. D. W. Cheng, Y. Tu, Z. W. Ma, Z. B. Niu, L. Q. Zhang. Risk assessment for networked-guarantee loans using high-order graph attention representation. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, pp. 5822–5828, 2019. DOI: https://doi.org/10.24963/ijcai.2019/807.

    Google Scholar 

  225. S. X. Rao, S. Zhang, Z. C. Han, Z. T. Zhang, W. Min, Z. Y. Chen, Y. N. Shan, Y. Zhao, C Zhang. xFraud: Explainable fraud transaction detection on heterogeneous graphs, [Online], Available: https://arxiv.org/abs/2011.12193, 2020.

    Google Scholar 

  226. M. H. Van, W. Du, X. T. Wu, A. D. Lu. Poisoning attacks on fair machine learning. In Proceedings of the 27th International Conference on Database Systems for Advanced Applications, Springer, pp. 370–386, 2022. DOI: https://doi.org/10.1007/978-3-031-00123-9_30.

    Chapter  Google Scholar 

  227. Z. N. Hu, Y. X. Dong, K. A. Wang, Y. Z. Sun. Heterogeneous graph transformer. In Proceedings of Web Conference 2020, ACM, Taipei, China, pp. 2704–2710, 2020. DOI: https://doi.org/10.1145/3366423.3380027.

    Chapter  Google Scholar 

  228. M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, M. Welling. Modeling relational data with graph convolutional networks. In Proceedings of the 15th International Conference on the Semantic Web, Springer, Heraklion, Greece, pp. 593–607, 2018. DOI: https://doi.org/10.1007/978-3-319-93417-4_38.

    Google Scholar 

  229. Z. Q. Zeng, R. Islam, K. N. Keya, J. Foulds, Y. Q. Song, S. M. Pan. Fair representation learning for heterogeneous information networks. In Proceedings of the 15th International AAAI Conference on Web and Social Media, AAAI, pp. 877–887, 2021. DOI: https://doi.org/10.1609/icwsm.v15i1.18111.

    Google Scholar 

  230. Y. R. Shrestha, Y. J. Yang. Fairness in algorithmic decision-making: Applications in multi-winner voting, machine learning, and recommender systems. Algorithms, vol. 12, no. 9, Article number 199, 2019. DOI: https://doi.org/10.3390/a12090199.

  231. T. Hashimoto, M. Srivastava, H. Namkoong, P. Liang. Fairness without demographics in repeated loss minimization. In Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, pp. 1929–1938, 2018.

    Google Scholar 

  232. T. X. Zhao, E. Y. Dai, K. Shu, S. H. Wang. You can still achieve fairness without sensitive attributes: Exploring biases in non-sensitive features, [Online], Available: https://arxiv.org/abs/2104.14537, 2021.

    Google Scholar 

  233. P. Lahoti, A. Beutel, J. L. Chen, K. Lee, F. Prost, N. Thain, X. Z. Wang, E. H. Chi. Fairness without demographics through adversarially reweighted learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 62, 2020.

    Google Scholar 

  234. Q. S. Zhang, S. C. Zhu. Visual interpretability for deep learning: A survey. Frontiers of Information Technology & Electronic Engineering, vol. 19, no. 1, pp. 27–39, 2018. DOI: https://doi.org/10.1631/FITEE.1700808.

    Article  Google Scholar 

  235. M. Nauta, J. Trienes, S. Pathak, E. Nguyen, M. Peters, Y. Schmitt, J. Schlötterer, M. van Keulen, C. Seifert. From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI. ACM Computing Surveys, vol. 55, no. 13s, pp. 295, 2023. DOI: https://doi.org/10.1145/3583558.

    Article  Google Scholar 

  236. S. Sharma, J. Henderson, J. Ghosh. CERTIFAI: A common framework to provide explanations and analyse the fairness and robustness of black-box models. In Proceedings of AAAI/ACM Conference on AI, Ethics, and Society, ACM, New York, USA, pp. 166–172, 2020. DOI: https://doi.org/10.1145/3375627.3375812.

    Chapter  Google Scholar 

  237. H. Baniecki, W. Kretowicz, P. Piątyszek, J. Wisniewski, P. Biecek. dalex: Responsible machine learning with interactive explainability and fairness in python. Journal of Machine Learning Research, vol. 22, no. 1, Article number214, 2021

  238. H. Yuan, H. Y. Yu, S. R. Gui, S. W. Ji. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5782–5799, 2023. DOI: https://doi.org/10.1109/TPAMI.2022.3204236.

    Google Scholar 

  239. Z. X. Zhang, Q. Liu, H. Wang, C. Q. Lu, C. Lee. Prot-GNN: Towards self-explaining graph neural networks. In Proceedings of the 36th AAAI/ACM Conference on AI, Ethics, and Society, AAAI, pp. 9127–9135, 2022. DOI: https://doi.org/10.1609/aaai.v36i8.20898.

    Google Scholar 

  240. L. Faber, A. K. Moghaddam, R. Wattenhofer. When comparing to ground truth is wrong: On evaluating gnn explanation methods. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM, Singapore, pp. 332–341, 2021. DOI: https://doi.org/10.1145/3447548.3467283.

    Chapter  Google Scholar 

  241. B. Mittelstadt, C. Russell, S. Wachter. Explaining explanations in AI. In Proceedings of Conference on Fairness, Accountability, and Transparency, ACM, Atlanta, USA, pp. 279–288, 2019. DOI: https://doi.org/10.1145/3287560.3287574.

    Chapter  Google Scholar 

  242. M. Danilevsky, K. Qian, R. Aharonov, Y. Katsis, B. Kawas, P. Sen. A survey of the state of explainable ai for natural language processing. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, ACL, Suzhou, China, pp. 447–459, 2020.

    Chapter  Google Scholar 

  243. D. S. Luo, W. Cheng, D. K. Xu, W. C. Yu, B. Zong, H. F. Chen, X. Zhang. Parameterized explainer for graph neural network. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1646, 2020.

    Google Scholar 

  244. J. L. Tang, X. Hu, S. W. Ji. XGNN: Towards model-level explanations of graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, USA, pp. 430–438, 2020. DOI: https://doi.org/10.1145/3394486.3403085.

    Google Scholar 

  245. F. Baldassarre, H. Azizpour. Explainability techniques for graph convolutional networks, [Online], Available: https://arxiv.org/abs/1905.13686, 2019.

    Google Scholar 

  246. W. J. Murdoch, C. Singh, K. Kumbier, R. Abbasi-Asl, B. Yu. Definitions, methods, and applications in interpretable machine learning. Proceedings of the National Academy of Sciences of the United States of America, vol. 116, no. 44, pp. 22071–22080, 2019. DOI: https://doi.org/10.1073/pnas.1900654116.

    Article  MathSciNet  Google Scholar 

  247. T. Kulesza, S. Stumpf, M. Burnett, S. Yang, I. Kwan, W. K Wong. Too much, too little, or just right? Ways explanations impact end users’ mental models. In Proceedings of IEEE Symposium on Visual Languages and Human Centric Computing, IEEE, San Jose, USA, pp. 3–10, 2013. DOI: https://doi.org/10.1109/VLHCC.2013.6645235.

    Google Scholar 

  248. M. Robnik-Šikonja, M. Bohanec. Perturbation-based explanations of prediction models. Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, J. L. Zhou, F. Chen, Eds., Cham, Switzerland: Springer, pp. 159–175, 2018. DOI: https://doi.org/10.1007/978-3-319-90403-0_9.

    Chapter  Google Scholar 

  249. D. Alvarez-Melis, T. S. Jaakkola. On the robustness of interpretability methods, [Online], Available: https://arxiv.org/abs/1806.08049, 2018.

    Google Scholar 

  250. T. Miller. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, vol. 267, pp. 1–38, 2019. DOI: https://doi.org/10.1016/j.artint.2018.07.007.

    Article  MathSciNet  Google Scholar 

  251. J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, B. Kim. Sanity checks for saliency maps. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 9525–9536, 2018.

    Google Scholar 

  252. P. Atanasova, J. G. Simonsen, C. Lioma, I. Augenstein. A diagnostic study of explainability techniques for text classification. In Proceedings of Conference on Empirical Methods in Natural Language Processing, ACL, pp. 3256–3274, 2020. DOI: https://doi.org/10.18653/v1/2020.emnlpmain.263.

    Google Scholar 

  253. J. Huysmans, K. Dejaeger, C. Mues, J. Vanthienen, B. Baesens. An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models. Decision Support Systems, vol. 51, no. 1, pp. 141–154, 2011. DOI: https://doi.org/10.1016/j.dss.2010.12.003.

    Article  Google Scholar 

  254. M. Bajaj, L. Y. Chu, Z. Y. Xue, J. Pei, L. J. Wang, P. C. H. Lam, Y. Zhang. Robust counterfactual explanations on graph neural networks. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Vancouver, Canada, pp. 5644–5655, 2021.

    Google Scholar 

  255. S. Verma, V. Boonsanong, M. Hoang, K. E. Hines, J. P. Dickerson, C. Shah. Counterfactual explanations and algorithmic recourses for machine learning: A review, [Online], Available: https://arxiv.org/abs/2010.10596, 2020.

    Google Scholar 

  256. W. Y. Lin, H. Lan, B. C. Li. Generative causal explanations for graph neural networks. In Proceedings of the 38th International Conference on Machine Learning, pp. 6666–6679, 2021.

    Google Scholar 

  257. Q. Huang, M. Yamada, Y. Tian, D. Singh, D. W. Yin, Y. Chang. GraphLIME: Local interpretable model explanations for graph neural networks, [Online], Available: https://arxiv.org/abs/2001.06216, 2020

    Google Scholar 

  258. J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, G. E. Dahl. Neural message passing for quantum chemistry. In Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, pp. 1263–1272, 2017.

    Google Scholar 

  259. P. E. Pope, S. Kolouri, M. Rostami, C. E. Martin, H. Hoffmann. Explainability methods for graph convolutional neural networks. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 10764–10773, 2019. DOI: https://doi.org/10.1109/CVPR.2019.01103.

    Google Scholar 

  260. R. Schwarzenberg, M. Hübner, D. Harbecke, C. Alt, L. Hennig. Layerwise relevance visualization in convolutional text graph classifiers. In Proceedings of the 13th Workshop on Graph-Based Methods for Natural Language Processing, ACL, Hong Kong, China, pp. 58–62, 2019. DOI: https://doi.org/10.18653/v1/D19-5308.

    Google Scholar 

  261. Y. Zhang, D. Defazio, A. Ramesh. ReLEx: A model-agnostic relational model explainer. In Proceedings of 2021 AAAI/ACM Conference on AI, Ethics, and Society, ACM, USA, pp. 1042–1049, 2021. DOI: https://doi.org/10.1145/3461702.3462562.

    Chapter  Google Scholar 

  262. M. N. Vu, M. T. Thai. PGM-explainer: Probabilistic graphical model explanations for graph neural networks. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1025, 2020.

    Google Scholar 

  263. W. T. Xiong, I. Ni’mah, J. M. G. Huesca, W. van Ipenburg, J. Veldsink, M. Pechenizkiy. Looking deeper into deep learning model: Attribution-based explanations of textcnn, [Online], Available: https://arxiv.org/abs/1811.03970, 2018.

    Google Scholar 

  264. D. Baehrens, T. Schroeter, S. Harmeling, M. Kawanabe, K. Hansen, K. R. Müller. How to explain individual classification decisions. Journal of Machine Learning Research, vol. 11, pp. 1803–1831, 2010

    MathSciNet  Google Scholar 

  265. M. Sundararajan, A. Taly, Q. Q. Yan. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, pp. 3319–3328, 2017.

    Google Scholar 

  266. Y. Y. Gao, T. Sun, R. Bhatt, D. Z. Yu, S. Hong, L. Zhao. GNES: Learning to explain graph neural networks. In Proceedings of IEEE International Conference on Data Mining, IEEE, Auckland, New Zealand, pp. 131–140, 2021. DOI: https://doi.org/10.1109/ICDM51629.2021.00023.

    Google Scholar 

  267. T. Funke, M. Khosla, A. Anand. Hard masking for explaining graph neural networks. In Proceedings of International Conference on Learning Representations, Vienna, Austria, 2021.

    Google Scholar 

  268. X. Wang, Y. X. Wu, A. Zhang, X. N. He, T. S. Chua. Causal screening to interpret graph neural networks. In Proceedings of International Conference on Learning Representations, Vienna, Austria, 2021.

    Google Scholar 

  269. A. Lucic, M. A. T. Hoeve, G. Tolomei, M. De Rijke, F. Silvestri. CF-GNNExplainer: Counterfactual explanations for graph neural networks. In Proceedings of the 25th International Conference on Artificial intelligence and Statistics, pp. 4499–4511, 2022.

    Google Scholar 

  270. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, Y. Bengio. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations, Vancouver, Canada, 2018.

    Google Scholar 

  271. X. Wang, Y. X. Wu, A. Zhang, X. N. He, T. S. Chua. Towards multi-grained explainability for graph neural networks. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Vancouver, Canada, 2021.

    Google Scholar 

  272. M. S. Schlichtkrull, N. De Cao, I. Titov. Interpreting graph neural networks for nlp with differentiable edge masking. In Proceedings of the 9th International Conference on Learning Representations, Austria, 2021.

    Google Scholar 

  273. S. Bach, A. Binder, G. Montavon, F. Klauschen, K. R. Müller, W. Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One, vol. 10, no. 7, Article number e0130140, 2015. DOI: https://doi.org/10.1371/journal.pone.0130140.

  274. J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller. Striving for simplicity: The all convolutional net. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2014. DOI: https://doi.org/10.48550/arXiv.1412.6806.

    Google Scholar 

  275. T. Schnake, O. Eberle, J. Lederer, S. Nakajima, K. T. Schütt, K. R. Müller, G. Montavon. Higher-order explanations of graph neural networks via relevant walks. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7581–7596, 2022. DOI: https://doi.org/10.1109/TPAMI.2021.3115452.

    Article  Google Scholar 

  276. H. Li, Z. Xu, G. Taylor, C. Studer, T. Goldstein. Visualizing the loss landscape of neural nets. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 6391–6401, 2018.

    Google Scholar 

  277. M. T. Ribeiro, S. Singh, C. Guestrin. “Why Should I Trust You?”: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, San Francisco, USA, pp. 1135–1144, 2016. DOI: https://doi.org/10.1145/2939672.2939778.

    Chapter  Google Scholar 

  278. Z. X. Huang, M. Kosan, S. Medya, S. Ranu, A. Singh. Global counterfactual explainer for graph neural networks. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining, ACM, Singapore, pp. 141–149, 2023. DOI: https://doi.org/10.1145/3539597.3570376.

    Google Scholar 

  279. Y. Yang, L. Song. Learn to explain efficiently via neural logic inductive learning. In Proceedings of the 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, 2019.

    Google Scholar 

  280. T. L. Wu, H. Y. Ren, P. Li, J. Leskovec. Graph information bottleneck. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1716, 2020.

    Google Scholar 

  281. Y. X. Wu, X. Wang, A. Zhang, X. N. He, T. S. Chua. Discovering invariant rationales for graph neural networks. In Proceedings of the 10th International Conference on Learning Representations, 2022.

    Google Scholar 

  282. S. H. Fan, X. Wang, Y. H. Mo, C. Shi, J. Tang. Debiasing graph neural networks via learning disentangled causal substructure. In Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 1808, 2022.

    Google Scholar 

  283. Y. Q. Chen, Y. G. Zhang, Y. T. Bian, H. Yang, K. L. Ma, B. H. Xie, T. L. Liu, B. Han, J. Cheng. Learning causally invariant representations for out-of-distribution generalization on graphs. In Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 1608, 2022.

    Google Scholar 

  284. M. H. Lin, T. Xiao, E. Y. Dai, X. Zhang, S. H. Wang. Certifiably robust graph contrastive learning. In Proceedings of the 37th International Conference on Neural Information Processing Systems, New Orleans, USA, 2023.

    Google Scholar 

  285. A. K. Debnath, R. L. L. de Compadre, G. Debnath, A. J. Shusterman, C. Hansch. Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. Journal of Medicinal Chemistry, vol. 34, no. 2, pp. 786–797, 1991. DOI: https://doi.org/10.1021/jm00106a046.

    Article  Google Scholar 

  286. Z. Q. Wu, B. Ramsundar, E. N. Feinberg, J. Gomes, C. Geniesse, A. S. Pappu, K. Leswing, V. Pande. Molecule-Net: A benchmark for molecular machine learning. Chemical Science, vol. 9, no. 2, pp. 513–530, 2018. DOI: https://doi.org/10.1039/C7SC02664A.

    Article  Google Scholar 

  287. J. Devlin, M. W. Chang, K. Lee, K. Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, ACL, Minneapolis, USA, pp. 4171–4186, 2019. DOI: https://doi.org/10.18653/v1/N19-1423.

    Google Scholar 

  288. T. Funke, M. Khosla, A. Anand. Zorro: Valid, sparse, and stable explanations in graph neural networks, [Online], Available: https://arxiv.org/abs/2105.08621, 2021.

    Google Scholar 

  289. E. Dai, S. H. Wang. Learning fair graph neural networks with limited and private sensitive attribute information. IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 7, pp. 7103–7117, 2023. DOI: https://doi.org/10.1109/TKDE.2022.3197554.

    Google Scholar 

  290. B. C. Zhang, Y. S. Dong, C. Chen, Y. D. Zhu, M. N. Luo, J. D. Li. Adversarial attacks on fairness of graph neural networks, [Online], Available: https://arxiv.org/abs/2310.13822, 2023.

    Google Scholar 

  291. H. Xu, X. R. Liu, Y. X. Li, A. Jain, J. L. Tang. To be robust or to be fair: Towards fairness in adversarial training. In Proceedings of the 38th International Conference on Machine Learning, pp. 11492–11501, 2021.

    Google Scholar 

  292. J. Adebayo, M. Muelly, I. Liccardi, B. Kim. Debugging tests for model explanations. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 60, 2020.

    Google Scholar 

  293. J. T. Tan, Y. F. Zhang. ExplainableFold: Understanding alphafold prediction with explainable AI. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Long Beach, USA, pp. 2166–2176, 2023. DOI: https://doi.org/10.1145/3580305.3599337.

    Chapter  Google Scholar 

  294. X. G. Sun, H. Cheng, J. Li, B. Liu, J. H. Guan. All in one: Multi-task prompting for graph neural networks. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, Long Beach, USA, pp. 2120–2131, 2023. DOI: https://doi.org/10.1145/3580305.3599256.

    Chapter  Google Scholar 

  295. Z. K. Chen, H. T. Mao, H. Li, W. Jin, H. Z. Wen, X. C. Wei, S. Q. Wang, D. W. Yin, W. Q. Fan, H. Liu, J. L. Tang. Exploring the potential of large language models (LLMs) in learning on graphs, [Online], Available: https://arxiv.org/abs/2307.03393, 2023.

    Google Scholar 

  296. J. W. Liu, C. Yang, Z. Y. Lu, J. Z. Chen, Y. B. Li, M. M. Zhang, T. Bai, Y. Fang, L. C. Sun, P. S. Yu, C. Shi. Towards graph foundation models: A survey and beyond, [Online], Available: https://arxiv.org/abs/2310.11829, 2023.

    Google Scholar 

Download references

Acknowledgements

This material is based upon work supported by, or in part by, the National Science Foundation (NSF), USA (No. IIS-1909702), the Army Research Office (ARO), USA (No. W911NF21-1-0198), and Department of Homeland Security (DNS) CINA, USA (No. E205949D). The findings in this paper do not necessarily reflect the view of the funding agencies.

Author information

Authors and Affiliations

  1. The Pennsylvania State University, State College, 16801, USA

    Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo & Suhang Wang

  2. Michigan State University, East Lansing, 48824, USA

    Hui Liu & Jiliang Tang

Authors
  1. Enyan Dai
    View author publications

    Search author on:PubMed Google Scholar

  2. Tianxiang Zhao
    View author publications

    Search author on:PubMed Google Scholar

  3. Huaisheng Zhu
    View author publications

    Search author on:PubMed Google Scholar

  4. Junjie Xu
    View author publications

    Search author on:PubMed Google Scholar

  5. Zhimeng Guo
    View author publications

    Search author on:PubMed Google Scholar

  6. Hui Liu
    View author publications

    Search author on:PubMed Google Scholar

  7. Jiliang Tang
    View author publications

    Search author on:PubMed Google Scholar

  8. Suhang Wang
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Suhang Wang.

Ethics declarations

Jiliang Tang is an Associate Editor for Machine Intelligence Research and was not involved in the editorial review, or the decision to publish this article. All authors declare that there are no other competing interests.

Additional information

Colored figures are available in the online version at https://link.springer.com/journal/11633

Enyan Dai received the B. Sc. degree in mechanical engineering from University of Science and Technology of China, China in and M. Sc. degree in AI from KU Leuven, Belgium in 2016. He is currently working towards the Ph. D. degree at the Pennsylvania State University, USA, under the supervision of Professor Suhang Wang. He has published innovative works in top conference proceedings such as ICLR, WSDM, KDD, CIKM, and ICWSM.

His research interests include data mining, graph neural networks, and trustworthy AI.

Tianxiang Zhao received the B. Sc. degree in computer science from University of Science and Technology of China (USTC), China in 2017. He is currently working toward the Ph.D. degree in IST at the Pennsylvania State University (PSU), USA, under the supervision of Dr. Suhang Wang and Dr. Xiang Zhang since 2019. He also worked as a research intern at NEC, USA (2021, 2022) and a research intern at Microsoft Research, USA (2023).

His research interests include graph neural networks, weak supervision tasks and knowledge transfer.

Huaisheng Zhu received the B. Sc. degree in computer science and engineering from Southern University of Science and Technology of China (Sustech), China in 2020. He is currently working toward the Ph. D. degree in IST at the Pennsylvania State University (PSU), USA, under the supervision of Dr. Vasant Honavar.

His research interests include diffusion models, multimodal generation and molecule generation.

Junjie Xu received the B.Sc. degree from Huazhong University of Science and Technology, China in 2021. He is currently a Ph. D. student at The Pennsylvania State University, USA.

His research interests include data mining, graph learning, large language model, and AI for science.

Zhimeng Guo received the B. Sc. degree in computer science from the University of Electronic Science and Technology of China (UESTC), China in 2021. He is currently working toward the Ph. D. degree in IST at the Pennsylvania State University (PSU), USA, under the supervision of Dr. Minhao Cheng.

His research interests include robustness and alignment of foundation models.

Hui Liu received the Ph. D. degree in electrical engineering from southern Methodist University, USA in 2015. She is an assistant professor in the Computer Science and Engineering Department at Michigan State University, USA.

Her research interests include trustworthy AI, designing data mining algorithms for wireless communication of smart devices, and applying machine learning and data mining in wireless communications.

Jiliang Tang received the Ph. D. degree in computer science from Arizona State University, USA in 2015. He is an associate professor in the Computer Science and Engineering Department at Michigan State University, USA. Before that, he was a research scientist in Yahoo Research, USA. He was the recipient of the 2021 ACSIC Rising Star Award, 2021 IEEE Big Data Security Junior Research Award, 2020 ACM SIGKDD Rising Star Award, 2020 Distinguished Withrow Research Award, 2019 NSF Career Award and 7 best paper (or runner up) awards including KDD2015 and WSDM2018. His dissertation won the 2015 KDD Best Dissertation runner-up and Dean’s Dissertation Award. He has served as the editors and the organizers in prestigious journals (e.g., TKDD) and conferences (e.g., KDD, WSDM, and SDM). He has filed more than 10 US patents and has published his research in highly ranked journals and top conference proceedings, which received more than 17 000 citations with h-index 62 and extensive media coverage.

His research interests include data mining, machine learning and their applications on social, web, and education domains.

Suhang Wang received the B. Sc. degree in electrical and computer engineering from Shanghai Jiao Tong University, China in 2012, the M. Sc. degree in electrical engineering from University of Michigan–Ann Arbor, USA in 2013, the Ph. D. degree in computer science from Arizona State University, USA in 2018. He is an assistant professor of the College of Information Sciences and technology, the Pennsylvania State University, USA. He is an Associate Editor for several journals and serves as regular journal reviewers and numerous conference program committees. He has published innovative works in highly ranked journals and top conference proceedings such as IEEE TKDE, ACM TIST, KDD, WWW, AAAI, IJCAI, CIKM, SDM, WSDM, ICDM and CVPR, which have received extensive coverage in the media.

His research interests include graph mining, data mining and machine learning.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dai, E., Zhao, T., Zhu, H. et al. A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability. Mach. Intell. Res. 21, 1011–1061 (2024). https://doi.org/10.1007/s11633-024-1510-8

Download citation

  • Received: 14 October 2023

  • Accepted: 07 April 2024

  • Published: 27 September 2024

  • Version of record: 27 September 2024

  • Issue date: December 2024

  • DOI: https://doi.org/10.1007/s11633-024-1510-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Keywords

  • Graph neural networks (GNNs)
  • trustworthy
  • privacy
  • robustness
  • fairness
  • explainability

Profiles

  1. Enyan Dai View author profile
Use our pre-submission checklist

Avoid common mistakes on your manuscript.

Advertisement

Search

Navigation

  • Find a journal
  • Publish with us
  • Track your research

Discover content

  • Journals A-Z
  • Books A-Z

Publish with us

  • Journal finder
  • Publish your research
  • Language editing
  • Open access publishing

Products and services

  • Our products
  • Librarians
  • Societies
  • Partners and advertisers

Our brands

  • Springer
  • Nature Portfolio
  • BMC
  • Palgrave Macmillan
  • Apress
  • Discover
  • Your US state privacy rights
  • Accessibility statement
  • Terms and conditions
  • Privacy policy
  • Help and support
  • Legal notice
  • Cancel contracts here

Not affiliated

Springer Nature

© 2025 Springer Nature