2 papers
cs.LG2026
Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning
Xinxun Zhang, Pengfei Jiao, Mengzhou Gao +2
Although dynamic graph neural networks (DyGNNs) have demonstrated promising capabilities, most existing methods ignore out-of-distribution (OOD) shifts that commonly exist in dynam…
cs.LG2024
Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graphs
Pengfe Jiao, Xinxun Zhang, Mengzhou Gao +2
Generative self-supervised learning (SSL), especially masked autoencoders (MAE), has greatly succeeded and garnered substantial research interest in graph machine learning. However…