Self-attention Dual Embedding for Graphs with Heterophily

Understand

Graph Neural Networks (GNNs) have been highly successful for the node classification task.

• GNNs typically assume graphs are homophilic, i.e.
• neighboring nodes are likely to belong to the same class.
• However, a number of real-world graphs are heterophilic, and this leads to much lower classification accuracy using standard GNNs.