Distance and Hop-wise Structures Encoding Enhanced Graph Attention Networks

no code implementations • 6 Dec 2021 • Zhiguo Huang, Xiaowei Chen, Bojuan Wang

Numerous works have proven that existing neighbor-averaging Graph Neural Networks cannot efficiently catch structure features, and many works show that injecting structure, distance, position or spatial features can significantly improve performance of GNNs, however, injecting overall structure and distance into GNNs is an intuitive but remaining untouched idea.

Graph Attention Position