My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
Why do you think that https://github.com/gordicaleksa/pytorch-learn-reinforcement-learning is a good alternative to pytorch-GAT