CARE: Contextual Affinity Exploration with Twin Concordance for Graph Out-Of-Distribution Detection

Yifan Wang, Haodong Zhang, Changhu Wang, Tao Ren, Wei Ju, Chong Chen, Xian-Sheng Hua, Xiao Luo

Keywords: Graph Neural Networks, Out-of-distribution Detection, Concordance Learning

Abstract:

This paper studies the problem of graph out-of-distribution (OOD) detection, which aims to identify anomaly graphs out of a graph dataset. Prior efforts usually focus on the utilization of topological structures with unsupervised graph learning to foster typical pattern recognition, which overlooks the semantic structure preserved in contextually affine neighborhoods. Towards this end, we propose a novel approach named Contextual Affinity Exploration with Twin Concordance (CARE) for graph OOD detection. The core of CARE is to explore and exploit the contextual affinity of the graph data samples for discriminative graph representations.
In particular, our CARE first builds a contextual affinity graph to depict the semantic structure in the hidden space. More importantly, we introduce high-order affinity to enhance geometric understanding of the structure by utilizing a meta-graph neural network. To enhance representation discriminability with high robustness, we introduce twin concordance learning, which not only minimizes the difference of affinity distributions across different views, but also encourages the consistency between contextually affinitive neighbors. Finally, we introduce a compression strategy to expand the decision boundary for enhanced separation between in-distribution and out-of-distribution graphs. Extensive experimental results demonstrate the superiority of our CARE across ten real datasets in comparison to various baselines.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 12073