用关系指纹对齐异构特征，提升通用图异常检测泛化能力
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
- 基于关系指纹编码上下文与结构线索，实现语义感知的特征对齐
- 在14个数据集上显著超越现有方法，最高提升12.3%
- 适合需要跨图迁移的异常检测场景，尤其对新图泛化要求高
通用图异常检测（GAD）旨在不进行图特定重训练的情况下，检测未知图中的异常。然而，现有方法主要依赖基于PCA的投影对齐异构特征，虽统一了特征维度，却忽略了特征语义。这导致模型难以学习可迁移的语义知识，甚至在未知图上出现负迁移。为此，我们提出一种基于关系指纹的通用图异常检测方法（ReFi-GAD），通过统一且语义感知的关系指纹（ReFi）对齐异构原始特征，该指纹从上下文和结构角度编码异常指示信号。在此基础上，设计了一种指纹引导的通用GAD模型，结合Transformer编码器捕捉域不变知识，以及信噪比引导的精炼模块实现域特定适应。在14个数据集上的大量实验表明，ReFi-GAD显著优于现有先进方法。
原文摘要 · Abstract (English)
Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining. Nevertheless, existing approaches primarily focus on aligning heterogeneous features across different data domains via PCA-based projection, which harmonizes feature dimensions ignores feature semantics. As a result, GAD models fail to learn transferable semantic knowledge, and even exhibit negative transfer on unseen graphs. To address this issue, we propose a Relational Fingerprint-based generalist GAD approach (ReFi-GAD for short), aligning heterogeneous raw features with a universal and semantics-aware Relational Fingerprint (ReFi) that encodes anomaly-indicative cues from both contextual and structural perspectives. Building on ReFi, we design a fingerprint-grounded generalist GAD model, which combines a transformer-based encoder to capture domain-invariant knowledge with an SNR-guided refinement module for domain-specific adaptation. Extensive experiments on 14 datasets demonstrate that ReFi-GAD significantly outperforms state-of-the-art methods.
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。