Distance and Hop-wise Structures Encoding Enhanced Graph Attention Networks
This work addresses a specific issue in graph learning for researchers, but it is incremental as it builds on existing GAT methods with added structural encodings.
The authors tackled the problem of Graph Neural Networks (GNNs) inefficiently capturing structure features by injecting hop-wise structure and distance distributional information into GATs, achieving competitive results as shown in experiments.
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. In this work, we shed light on the direction. We first extracting hop-wise structure information and compute distance distributional information, gathering with node's intrinsic features, embedding them into same vector space and then adding them up. The derived embedding vectors are then fed into GATs(like GAT, AGDN) and then Correct and Smooth, experiments show that the DHSEGATs achieve competitive result. The code is available at https://github.com/hzg0601/DHSEGATs.