2 papers
cs.LG2026
Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization
Yang Qiu, Yixiong Zou, Jun Wang
Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a preva…
cs.LG2025
Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
Yang Qiu, Yixiong Zou, Jun Wang +3
Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimizat…