GT-A 2 T: Graph Tensor Alliance Attention Network
Ling Wang, Kechen Liu, Ye Yuan · IEEE/CAA Journal of Automatica Sinica · 2024
Dear Editor, This letter proposes the graph tensor alliance attention network (GT-A2T) to represent a dynamic graph (DG) precisely. Its main idea includes 1) Establishing a unified spatio-temporal message propagation framework on a DG via the tensor product for capturing the complex cohesive spatio-temporal interdependencies precisely and 2) Acquiring the alliance attention scores by node features and favorable high-order structural correlations. Empirical studies on DG benchmark datasets indicate that the proposed GT-A2T consistently outperforms the state-of-the-art models in the field of missing link weight estimation and link prediction.