Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914050499149824 |
|---|---|
| author | Xu, Xiaoyang Lin, Xiaofeng Takeuchi, Koh Atarashi, Kyohei Kashima, Hisashi |
| author_facet | Xu, Xiaoyang Lin, Xiaofeng Takeuchi, Koh Atarashi, Kyohei Kashima, Hisashi |
| contents | Anomaly detection in dynamic graphs is a critical task with broad real-world applications, including social networks, e-commerce, and cybersecurity. Most existing methods assume that normal patterns remain stable over time; however, this assumption often fails in practice due to the phenomenon we refer to as normality distribution shift (NDS), where normal behaviors evolve over time. Ignoring NDS can lead models to misclassify shifted normal instances as anomalies, degrading detection performance. To tackle this issue, we propose WhENDS, a novel unsupervised anomaly detection method that aligns normal edge embeddings across time by estimating distributional statistics and applying whitening transformations. Extensive experiments on four widely-used dynamic graph datasets show that WhENDS consistently outperforms nine strong baselines, achieving state-of-the-art results and underscoring the importance of addressing NDS in dynamic graph anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17400 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs Xu, Xiaoyang Lin, Xiaofeng Takeuchi, Koh Atarashi, Kyohei Kashima, Hisashi Machine Learning Anomaly detection in dynamic graphs is a critical task with broad real-world applications, including social networks, e-commerce, and cybersecurity. Most existing methods assume that normal patterns remain stable over time; however, this assumption often fails in practice due to the phenomenon we refer to as normality distribution shift (NDS), where normal behaviors evolve over time. Ignoring NDS can lead models to misclassify shifted normal instances as anomalies, degrading detection performance. To tackle this issue, we propose WhENDS, a novel unsupervised anomaly detection method that aligns normal edge embeddings across time by estimating distributional statistics and applying whitening transformations. Extensive experiments on four widely-used dynamic graph datasets show that WhENDS consistently outperforms nine strong baselines, achieving state-of-the-art results and underscoring the importance of addressing NDS in dynamic graph anomaly detection. |
| title | Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.17400 |