3 papers
cs.LG2026
Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability
Jialiang Yin, Zheng Zhao, Linsey Pang +3
Graph Neural Networks (GNNs) have demonstrated remarkable performance across a range of applications involving graph-structured data, particularly in high-stakes domains. However,…
cs.LG2026
Beyond Parameter Finetuning: Test-Time Representation Refinement for Node Classification
Jiaxin Zhang, Yiqi Wang, Siwei Wang +4
Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising solution, e…
cs.SI2024
Mixture of Experts for Node Classification
Yu Shi, Yiqi Wang, WeiXuan Lang +3
Nodes in the real-world graphs exhibit diverse patterns in numerous aspects, such as degree and homophily. However, most existent node predictors fail to capture a wide range of no…