NLPGNN

1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing. Maintained by kaiyinzhou on GitHub, where it has earned 335 stars from the community.

It's actively developed around tensorflow2, bert, gpt2, and is a solid reference for anyone building with these tools.