发表机构
Islamic University of Technology; University of Southern California; King Fahd University of Petroleum & Minerals（伊斯兰科技大学; 南加利福尼亚大学; 法赫德国王石油与矿业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RINSE是一种无梯度的目标时刻框架，通过识别可靠节点子集构建目标感知正态性模型，结合多种技术提升零样本图异常检测性能，在8个目标图上取得最高平均AUPRC。
AI 中文摘要
零样本图异常检测旨在将在源图上训练的检测器部署到未见的、未标记的目标图上，但域偏移会导致源自源数据的正态性概念不可靠。我们提出RINSE（鲁棒迭代正态性自估计，Robust Iterative Normality Self-Estimation），这是一种无梯度的目标时刻框架，它保持源训练的检测器固定，同时从目标图中依次估计目标正态性、表示校准和证据可靠性。其核心思路是识别低残差的可靠目标节点子集，用它们构建修剪后的目标感知正态性模型，并通过可靠性门控秩融合和编码器集成结合互补的异常证据。在8个未见目标图上，RINSE在两种独立预处理协议下的评估方法中实现了最高的平均AUPRC，而块消融和敏感性分析支持其组合设计。这些结果表明，鲁棒目标时刻估计是一种无需目标标签、梯度或每个目标调优的通用图异常检测的实用方法。
英文摘要
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.
