Anchorgt: A Novel Attention Architecture For Graph Transformers As A Flexible Building Block To Improve The Scalability Of A Wide Range Of Graph Transformer Models

AnchorGT is a new graph Transformer model that addresses the scalability challenge of classic Transformers when dealing with graph data. By strategically choosing a small set of “anchor” nodes, AnchorGT significantly reduces the computational burden while still capturing global information. This approach offers an elegant solution to the limitations of previous works and preserves the expressive power of Transformers.