Proceedings

ABNet: Mitigating Sample Imbalance in Anomaly Detection Within Dynamic Graphs

Yifan Hong, Muhammad Asif Ali, Huan Wang, Junyang Chen, Di Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2910-2918.

https://doi.org/10.24963/ijcai.2025/324

Keywords

  • Data Mining: DM: Class imbalance and unequal cost
  • Data Mining: DM: Networks
  • Data Mining: DM: Anomaly/outlier detection

Abstract

In dynamic graphs, detecting anomalous nodes faces challenges due to sample imbalance, stemming from the scarcity of anomalous samples and feature representation bias. Existing methods often use unsupervised or semi-supervised learning to extract anomalous samples from unlabeled data, but struggle to obtain enough anomalous instances due to their low occurrence. Moreover, GNN-based approaches often prioritize normal samples, neglecting rare anomalies. To address these issues, we propose the Anomaly Balance Network (ABNet), designed to alleviate sample imbalance and enhance anomaly detection. ABNet includes three key components: a feature extractor that compares node features across time points to avoid bias, an anomaly augmenter that amplifies anomaly details and generates diverse anomalous samples, and an anomaly detector using meta-learning to adapt to graph evolution. Experimental results show that ABNet outperforms existing methods on three real-world datasets, effectively addressing sample imbalance.

Yifan Hong, Muhammad Asif Ali, Huan Wang, Junyang Chen, and Di Wang. 2025. ABNet: Mitigating Sample Imbalance in Anomaly Detection Within Dynamic Graphs. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2910–2918. https://doi.org/10.24963/ijcai.2025/324
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards