Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks

arXiv:2404.03139v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) often perform better for high-degree nodes than low-degree nodes on node classification tasks. This degree bias can reinforce social marginalization by, e.g., sidelining authors of lowly-cited papers when predicting paper topics in citation networks. While researchers have proposed numerous hypotheses for why GNN degree bias occurs, we find via a survey of 38 degree bias papers that these hypotheses are often not rigorously validated, and can even be contradictory. Thus, we …

abstract arxiv authors bias classification cs.lg cs.si gnns graph graph neural networks insights low networks neural networks node nodes paper papers reinforce researchers social tasks topics type