Proceedings

Multi-View Ensemble for Time Series Anomaly Detection via Coupling Flows

Wanghui Qiu, Chenxi Liu, Shiyan Hu, Zhengyu Li, Chenjuan Guo, Bin Yang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2988-2996.

https://doi.org/10.24963/ijcai.2026/332

Keywords

  • Data Mining: Mining spatial and/or temporal data

Abstract

Time series anomaly detection faces a critical challenge that different anomaly types require different detection mechanisms, yet single methods are inherently limited by their design biases. We propose FlowFuse, a multi-view ensemble framework with coupling flow-based score fusion for time series anomaly detection. FlowFuse combines four complementary detection modules spanning temporal and frequency domains, as well as clustering and reconstruction paradigms, to extract multi-perspective anomaly scores. Rather than simple averaging, an ensemble of coupling flows models the joint distribution of these multi-view scores, learning complex inter-view dependencies through invertible transformations with alternating updates between temporal and frequency scores. The ensemble naturally quantifies detection uncertainty through prediction disagreement, which can optionally guide selective supervision when labels are available. Extensive experiments across 18 diverse benchmarks show that FlowFuse achieves state-of-the-art performance, demonstrating effectiveness across multiple anomaly types.

Wanghui Qiu, Chenxi Liu, Shiyan Hu, Zhengyu Li, Chenjuan Guo, and Bin Yang. 2026. Multi-View Ensemble for Time Series Anomaly Detection via Coupling Flows. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 2988–2996. https://doi.org/10.24963/ijcai.2026/332
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards