Low-rank and global-representation-key-based attention for graph transformer

Lingping Kong, Varun Ojha, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan, Václav Snásel

Abstract: Highlights•We propose a Global-Representation-based attention mechanism for graph neural network.•The low-rank mechanism provides structural information on neighbor nodes.•We address over-smoothing and heterophily issues by various compositions of mechanism.•We justify its effectiveness and superiority with eight widely used tasks.•The proposed model ranks first by statistical analysis compared with seven algorithms.