Sep 2026
Dynamic graph representation learning based on multi-scale attention.
A Multi-scale Attention-based Dynamic Graph Network (MADGN) integrating structure-aware modeling and hierarchical attention is proposed, which outperforms state-of-the-art baselines on dynamic link prediction, dynamic new link prediction, and node classification tasks.
Ping-Tao Duan, Yan-Qun Wu, Jia-Yi Wei et al.
· Neural Networks · 0 citations