Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
This work addresses the challenge of OOD detection in graph data for real-world applications, representing an incremental advance over existing methods.
The paper tackles the problem of inaccurate predictions due to out-of-distribution (OOD) samples in graph classification by proposing RedOUT, an unsupervised framework that reduces structural redundancy, achieving an average improvement of 6.7% and surpassing the best competitor by 17.3% on a specific dataset pair.
Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) samples in real-world applications. Although existing graph OOD detection methods leverage data-centric techniques to extract effective representations, their performance remains compromised by structural redundancy that induces semantic shifts. To address this dilemma, we propose RedOUT, an unsupervised framework that integrates structural entropy into test-time OOD detection for graph classification. Concretely, we introduce the Redundancy-aware Graph Information Bottleneck (ReGIB) and decompose the objective into essential information and irrelevant redundancy. By minimizing structural entropy, the decoupled redundancy is reduced, and theoretically grounded upper and lower bounds are proposed for optimization. Extensive experiments on real-world datasets demonstrate the superior performance of RedOUT on OOD detection. Specifically, our method achieves an average improvement of 6.7%, significantly surpassing the best competitor by 17.3% on the ClinTox/LIPO dataset pair.