Abstract: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.
| Comments: | 9 pages, 7 figures. Accepted by ICML 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.25429 [cs.LG] |
| (or arXiv:2605.25429v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.25429 arXiv-issued DOI via DataCite (pending registration) |
From: Yujing Liu [view email]
[v1]
Mon, 25 May 2026 05:12:26 UTC (2,002 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。