FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection

Zhao, Yunfeng; Liu, Yixin; Chen, Qingfeng; Li, Shiyuan; Tan, Yue; Pan, Shirui

doi:10.24963/ijcai.2026/366

FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection

Yunfeng Zhao, Yixin Liu, Qingfeng Chen, Shiyuan Li, Yue Tan, Shirui Pan

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3294-3302.

https://doi.org/10.24963/ijcai.2026/366

Keywords

Machine Learning: Federated learning
Data Mining: Anomaly/outlier detection
Data Mining: Mining graphs
Machine Learning: Unsupervised learning

Abstract

Graph-level anomaly detection (GLAD) is crucial for ensuring the reliability of graph-driven applications by identifying abnormal graphs that deviate from the majority. Considering the privacy concerns in distributed scenarios, federated graph-level anomaly detection (FedGLAD) has emerged as a promising solution to enable collaborative detection without sharing raw data. However, existing methods suffer from poor generalization due to the reliance on unrealistic synthetic anomalies and insufficient personalization capabilities under data heterogeneity. To address these challenges, we propose a novel Federated graph-level anomaly detection approach with Cluster-adaptIve GAted Reconstruction (FedCIGAR). Specifically, we design a reconstruction-based paradigm trained on normal graphs to avoid synthetic data. Furthermore, we introduce a client-side node contribution gating mechanism and a server-side sliding window-based clustering strategy to tackle data heterogeneity. Extensive experiments demonstrate that FedCIGAR achieves superior performance and robustness compared to state-of-the-art methods.

Yunfeng Zhao, Yixin Liu, Qingfeng Chen, Shiyuan Li, Yue Tan, and Shirui Pan. 2026. FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3294–3302. https://doi.org/10.24963/ijcai.2026/366

@inproceedings{ijcai2026p366,
  title     = {FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection},
  author    = {Zhao, Yunfeng and Liu, Yixin and Chen, Qingfeng and Li, Shiyuan and Tan, Yue and Pan, Shirui},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {3294--3302},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/366},
  url       = {https://doi.org/10.24963/ijcai.2026/366},
}

TY  - CPAPER
TI  - FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection
AU  - Zhao, Yunfeng
AU  - Liu, Yixin
AU  - Chen, Qingfeng
AU  - Li, Shiyuan
AU  - Tan, Yue
AU  - Pan, Shirui
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 3294
EP  - 3302
DO  - 10.24963/ijcai.2026/366
UR  - https://doi.org/10.24963/ijcai.2026/366
ER  -