Temporal resonant graph network for representation learning on dynamic graphs

Zidu Yin, Kun Yue

Abstract: Generating dynamic node representation via limited samples at a time is a challenging task. Meanwhile, the human brain can quickly capture dynamic features without much information in a changing environment. Motivated by the idea of brain functions from the adaptive resonance theory (ART), in this paper, we designed and built a dynamic model for node representation generation. Based on the data flow of the ART model, we replaced the classic ART components with deep learnable modules. Our proposed method is suitable for capturing different graph evolution events even with very sparse changes. Experimental results on several synthetic and real-world dynamic graphs for many vital applications show the superiority of our proposed method.