无需目标标签或调参，实现零样本图异常检测的鲁棒性估计
RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection
- 通过筛选低残差节点构建目标感知的正常性模型
- 在8个未见图上平均AUPRC领先其他方法
- 适合无标注目标图的通用异常检测场景
零样本图异常检测旨在将源图上训练的检测器部署到未见、无标签的目标图中，但域偏移可能导致源图衍生的正常性定义不可靠。本文提出RINSE（Robust Iterative Normality Self-Estimation），一种无需梯度的靶向时间框架，在保持源训练检测器不变的前提下，依次估计目标图的正常性、表示校准和证据可靠性。其核心思想是识别一组低残差的目标节点，用以构建截断后的目标感知正常性模型，并通过可靠性门控排名融合与编码器集成结合互补异常证据。在八个未见目标图上，RINSE在两种不同预处理协议下均取得最高平均AUPRC；块消融实验与敏感性分析支持其联合设计的有效性。结果表明，无需目标标签、梯度或逐目标调参，靶向时间估计是一种实用的通用图异常检测方法。
原文摘要 · Abstract (English)
Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality unreliable. We introduce RINSE (Robust Iterative Normality Self-Estimation), a gradient-free target-time framework that keeps the source-trained detector fixed while sequentially estimating target normality, representation calibration, and evidence reliability from the target graph. Its core idea is to identify a reliable subset of low-residual target nodes, use them to construct a trimmed target-aware normality model, and combine complementary anomaly evidence through reliability-gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC among the evaluated methods under two separate preprocessing protocols, while block ablations and sensitivity analyses support the combined design. These results support robust target-time estimation as a practical approach to generalist graph anomaly detection without target labels, gradients, or per-target tuning.
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。