通过降低图结构冗余，提升测试时异常样本检测精度。
Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
- 引入结构熵机制，分离图数据中的有效信息与冗余内容。
- 在ClinTox/LIPO数据集上比最强基线提升17.3%。
- 无需标注，适合真实场景中模型可靠性评估。
训练与测试数据之间的分布差异会导致模型在真实应用中遇到异常样本时产生错误预测。尽管现有图神经网络异常检测方法采用数据驱动技术提取有效表征，但其性能仍受结构冗余引发的语义偏移影响。为此，我们提出RedOUT——一种无监督框架，将结构熵引入测试时图分类异常检测。具体地，提出冗余感知图信息瓶颈（ReGIB），将目标分解为本质信息与无关冗余。通过最小化结构熵，解耦冗余成分，并给出理论支持的上下界用于优化。大量实验证明RedOUT在异常检测上表现优异：在真实数据集上平均提升6.7%，尤其在ClinTox/LIPO数据集对上超越最佳基线17.3%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。