[Blog] Understand Graph Attention Network


From Graph Convolutional Network (GCN), we learned that combining local graph structure and node-level features yields good performance on node classification task. However, the way GCN aggregates is structure-dependent, which may hurt its generalizability.

This is a companion discussion topic for the original entry at https://www.dgl.ai/blog/2019/02/17/gat.html


Complete code and notebook of this tutorial is available here: https://docs.dgl.ai/tutorials/models/1_gnn/9_gat.html.