AnchorGT: Efficient and Flexible Attention Architecture for Scalable Graph Transformers

arXiv:2405.03481v1 Announce Type: new
Abstract: Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power. However, the quadratic complexity of self-attention mechanism in GTs has limited their scalability, and previous approaches to address this issue often suffer from expressiveness degradation or lack of versatility. To address this issue, we propose AnchorGT, a novel attention architecture for GTs with global receptive field …

abstract advanced architecture arxiv attention complexity cs.lg gnns graph graph neural networks graph representation however limitations networks neural networks performance power representation representation learning scalability scalable self-attention transformers type