Graph Propagation Transformer for Graph Representation Learning
This work addresses the problem of improving graph learning for researchers and practitioners, but it appears incremental as it builds on existing transformer-based methods with a novel attention mechanism.
The paper tackles graph representation learning by introducing a transformer architecture with a Graph Propagation Attention mechanism that explicitly passes information among nodes and edges, and results show it outperforms state-of-the-art transformer-based graph models on benchmark datasets.
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.