Graph Propagation Transformer for Graph Representation Learning

TL;DR

This paper introduces Graph Propagation Transformer (GPTrans), a novel architecture that enhances graph representation learning by explicitly propagating information among nodes and edges using a new attention mechanism, outperforming existing models.

Contribution

The paper proposes Graph Propagation Attention (GPA) and GPTrans, a transformer architecture that explicitly models information flow in graphs, advancing graph neural network capabilities.

Findings

GPTrans outperforms state-of-the-art transformer-based graph models.

The new attention mechanism effectively captures node and edge interactions.

Experimental results on benchmark datasets validate the approach.

Abstract

This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks. Specifically, we propose a new attention mechanism called Graph Propagation Attention (GPA). It explicitly passes the information among nodes and edges in three ways, i.e. node-to-node, node-to-edge, and edge-to-node, which is essential for learning graph-structured data. On this basis, we design an effective transformer architecture named Graph Propagation Transformer (GPTrans) to further help learn graph data. We verify the performance of GPTrans in a wide range of graph learning experiments on several benchmark datasets. These results show that our method outperforms many state-of-the-art transformer-based graph models with better performance. The code will be released at https://github.com/czczup/GPTrans.