跨域图异常检测新框架，测试时自适应提升效果。
Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervision
- 测试时用同质性引导的自监督学习，动态调整边权重
- 跨域场景下平均AUC提升8.2%以上，优于现有方法
- 适合标签稀疏、数据分布不同的真实图数据场景
图异常检测在识别图结构数据中的异常模式方面表现优异。然而，在新兴应用中，标注异常通常稀缺，且现有监督式图异常检测方法在跨图域迁移时因分布偏移和异构特征空间而失效或不适用。为此，我们提出GADT3，一种新型的测试时训练框架，用于跨域图异常检测。GADT3在训练阶段结合监督与自监督学习，测试时仅通过自监督学习适应新域，利用基于同质性的亲和度得分捕捉异常的域不变特性。该框架引入四项关键创新：有效的自监督机制、消息传递中动态学习边重要性权重的注意力机制、处理异构特征的域特定编码器，以及缓解类别不平衡的类别感知正则化。在多个跨域设置下的实验表明，GADT3显著优于现有方法，相比最佳对比模型，平均提升超过8.2%的AUROC和AUPRC。
原文摘要 · Abstract (English)
Graph Anomaly Detection (GAD) has demonstrated great effectiveness in identifying unusual patterns within graph-structured data. However, while labeled anomalies are often scarce in emerging applications, existing supervised GAD approaches are either ineffective or not applicable when moved across graph domains due to distribution shifts and heterogeneous feature spaces. To address these challenges, we present GADT3, a novel test-time training framework for cross-domain GAD. GADT3 combines supervised and self-supervised learning during training while adapting to a new domain during test time using only self-supervised learning by leveraging a homophily-based affinity score that captures domain-invariant properties of anomalies. Our framework introduces four key innovations to cross-domain GAD: an effective self-supervision scheme, an attention-based mechanism that dynamically learns edge importance weights during message passing, domain-specific encoders for handling heterogeneous features, and class-aware regularization to address imbalance. Experiments across multiple cross-domain settings demonstrate that GADT3 significantly outperforms existing approaches, achieving average improvements of over 8.2\% in AUROC and AUPRC compared to the best competing model.
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。