2021/09/27 by Xu Yan, Yan Xu, Yan, Xu +14 · 2 citations
Computer Science · Mathematics · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Artificial intelligence #Block (permutation group theory) #Complex Network Analysis Techniques #Computer science #Embedding #FOS: Computer and information sciences #Feature learning #Inference #Machine Learning (cs.LG) #Mathematics #Node (physics) #Representation (politics) #Social and Information Networks (cs.SI) #Theoretical computer science #Topic Modeling #cs.AI #cs.LG #cs.SI
paper · pdf · doi:10.48550/arxiv.2110.06088
published in arXiv (Cornell University) (Cornell University) · 12 pages; 6 figures
arxiv created 2021/09/27 · openalex publication_date 2021/09/27 · arxiv updated 2021/10/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes' state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction.