most citedGraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

4 citations · 4 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2023★ 4 cited

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

Mingxuan Ju, Tong Zhao, Wenhao Yu +2

Recent studies have shown that graph neural networks (GNNs) exhibit strong biases towards the node degree: they usually perform satisfactorily on high-degree nodes with rich neighb…