Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection

arXiv:2403.10339v1 Announce Type: new
Abstract: Graph-based anomaly detection is currently an important research topic in the field of graph neural networks (GNNs). We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs. For the first time, we introduce a new metric called Class Homophily Variance, which quantitatively describes this phenomenon. To mitigate its impact, we propose a novel GNN model named Homophily Edge Generation Graph Neural …

abstract anomaly anomaly detection arxiv class cs.lg detection differences distribution gnns graph graph-based graph neural networks graphs networks neural networks research type variance