Can I read SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning on EtoBox?

SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning by Chen, Jinsong; Li, Gaichao; Hopcroft, John E.; He, Kun is a scholarly article available to read on EtoBox.

What is SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning about?

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a two-step aggregation operation on a fully connected graph. Due to the property of generating positive attention values, the self-attention mechanism is equal to conducting a smooth operation on all nodes, preserving the low-frequency information. However, only capturing the low-frequency information is inefficient in learning complex relations of nodes on diverse graphs, such as heterophily graphs where the high-frequency information is crucial. To this end, we propose a Signed Attention-based Graph Transformer (SignGT) to adaptively capture various frequency information from the graphs. Specifically, SignGT develops a new signed self-attention mechanism (SignSA) that produces signed attention values according to the semantic relevance of node pairs. Hence, the diverse frequency information between different node pairs could be carefully preserved. Besides, SignGT proposes a structure-aware feed-forward network (SFFN) that introduces the neighborhood

Author

Chen, Jinsong; Li, Gaichao; Hopcroft, John E.; He, Kun

Published

2023

Language

EN