MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning

Federated graph anomaly detection (GAD) aims to identify abnormal nodes in distributed subgraphs through federated learning. However, existing methods suffer from two limitations. 1) Their reliance on neighborhood aggregation assumes that anomalous information can be sufficiently captured, which often fails in federated learning with partitioned client subgraphs. 2) They overlook the detection bottleneck caused by weak attribute or structural anomalies. To tackle these challenges, we revisit federated GAD and reveal that weak anomalies exhibit harder-to-detect signals compared to strong anomalies. Specifically, we propose MV-FGAD, an efficient and effective federated GAD framework for mining anomalies of varying strengths. MV-FGAD introduces a federated knowledge learning module to aggregate and broadcast shared knowledge, which is further exploited to optimize local topological structures. Moreover, it designs a multi-view learning mechanism to capture diverse anomaly patterns, and adopts Mahalanobis distance–based scoring strategy to quantify node abnormality across views. Extensive experiments on real-world datasets of varying types and scales demonstrate MV-FGAD's efficiency and effectiveness. Our code is publicly available at https://github.com/Junyi-Yan/MV-FGAD.

Modern applications such as social networks, financial systems, and online platforms often store graph-structured data across multiple devices or organizations, making it difficult to jointly detect suspicious or abnormal behaviors without sharing private data. Existing federated anomaly detection methods often struggle when the data are fragmented across different locations, especially when abnormal patterns are subtle and difficult to distinguish from normal ones. In this work, we propose MV-FGAD, a federated framework that improves anomaly detection on distributed graph data while preserving data privacy. Our method allows different participants to share useful knowledge without exposing their raw data, and combines information from multiple perspectives to better identify both obvious and subtle anomalies. Experiments on a variety of real-world datasets show that our approach achieves more accurate and stable detection while remaining communication-efficient. Our code is publicly available at https://github.com/Junyi-Yan/MV-FGAD.