CI and TensorFlow compatibility updates and stabilize examples checks

- merge CI workflows into a single matrix-based pipeline
- align examples/notebooks imports with tensorflow.keras
- add examples smoke tests and fast mode for run_ncf.py in CI
- fix ragged genres sequence handling in preprocess for TF2.10/NumPy
- encode genres in run_ncf.py for shared preprocess compatibility

add comirec model

add comirec model

refactor & add some negative sampling strategies (#81)

Support different negative sampling strategies, including `inbatch`, `uniform`, `frequency`, `adaptive`.
1. add `deepmatch.utils.NegativeSampler`
2. remove `deepmatch.layers.core.NegativeSampler`
3. add `temperature`,`sampler_config`,`loss_type` for models
4. add some google colab scripts

v0.2.1 release

v0.2.1 release

v0.2.0

Support different initializers for different embedding weights and loading pretrained embeddings

Add SDM model

support saving&loading model and higher version tf

- support saving&loading model
- support higher version of tensorflow

v0.1.1

v0.1.1