aiqbench analysis
AlignGAD introduces a zero-shot framework for cross-domain graph anomaly detection, addressing the critical limitation of existing methods that rely on dataset-specific patterns. By unifying heterogeneous features in the spectral domain and leveraging node reconstruction discrepancies, this approach enables robust identification of abnormal nodes in unseen graphs without task-specific fine-tuning. The work advances machine learning capabilities for handling complex, real-world heterogeneous data structures where generalization is essential.
A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction
arXiv:2606.12673v2 Announce Type: replace-cross Abstract: Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature semantics and structural patterns, which limits their ability to generalize across different domains. To address this challenge, we propose AlignGAD, a zero-shot generalized graph anomaly detection framework. Our framework is built upon three key components: a Global Unification Module that aligns heterogeneous node features and normalizes graph signals in the spectral domain; a Clustering Module that constructs cluster-aware graph views to capture group-level abnormal patterns; and a Node Discrepancy Scoring Module that measures reconstruction discrepancy and aggregates anomaly evidence from different graph views. Experiments on multiple real-world datasets demonstrate the effectiveness of AlignGAD under the zero-shot GAD setting.
Abstract:Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature semantics and structural patterns, which limits their ability to generalize across different domains. To address this challenge, we propose AlignGAD, a zero-shot generalized graph anomaly detection framework. Our framework is built upon three key components: a Global Unification Module that aligns heterogeneous node features and normalizes graph signals in the spectral domain; a Clustering Module that constructs cluster-aware graph views to capture group-level abnormal patterns; and a Node Discrepancy Scoring Module that measures reconstruction discrepancy and aggregates anomaly evidence from different graph views. Experiments on multiple real-world datasets demonstrate the effectiveness of AlignGAD under the zero-shot GAD setting.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.12673 [cs.LG]
(or arXiv:2606.12673v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.12673 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 225 words
Related coverage
A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction
arXiv · Jun 12, 2026
Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
arXiv · Sep 1, 2026
RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection
arXiv · Sep 3, 2026
Presentation: Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery
InfoQ · May 27, 2026