Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks
Multivariate time series anomaly detection is a challenging problem because there can be a number of complex relationships between variables in multivariate time series. Although graph neural networks have been shown to be effective in capturing variable-variable relationships (i.e. relationships be...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2025.2538519 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849254121147727872 |
|---|---|
| author | Tae Wook Ha Myoung Ho Kim |
| author_facet | Tae Wook Ha Myoung Ho Kim |
| author_sort | Tae Wook Ha |
| collection | DOAJ |
| description | Multivariate time series anomaly detection is a challenging problem because there can be a number of complex relationships between variables in multivariate time series. Although graph neural networks have been shown to be effective in capturing variable-variable relationships (i.e. relationships between two variables), they are hard to capture variable-group relationships (i.e. relationships between variables and groups of variables). To overcome this limitation, we propose a novel method called DHG-AD for multivariate time series anomaly detection. DHG-AD employs directed hypergraphs to model variable-group relationships within multivariate time series. For each time window, DHG-AD constructs two different directed hypergraphs to represent relationships between variables and groups of positively and negatively correlated variables, enabling the model to capture both types of relationships effectively. The directed hypergraph neural networks learn node representations from these hypergraphs, allowing comprehensive multivariate interaction modeling for anomaly detection. We show through experiments using various evaluation metrics that our proposed method achieves the best scores among the compared methods on two real-world datasets. |
| format | Article |
| id | doaj-art-e2d78e2b67064fcbac9c434ebb9c66da |
| institution | Kabale University |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-e2d78e2b67064fcbac9c434ebb9c66da2025-08-20T03:56:08ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452025-12-0139110.1080/08839514.2025.2538519Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural NetworksTae Wook Ha0Myoung Ho Kim1School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, Republic of KoreaSchool of Computing, Korea Advanced Institute of Science and Technology, Daejeon, Republic of KoreaMultivariate time series anomaly detection is a challenging problem because there can be a number of complex relationships between variables in multivariate time series. Although graph neural networks have been shown to be effective in capturing variable-variable relationships (i.e. relationships between two variables), they are hard to capture variable-group relationships (i.e. relationships between variables and groups of variables). To overcome this limitation, we propose a novel method called DHG-AD for multivariate time series anomaly detection. DHG-AD employs directed hypergraphs to model variable-group relationships within multivariate time series. For each time window, DHG-AD constructs two different directed hypergraphs to represent relationships between variables and groups of positively and negatively correlated variables, enabling the model to capture both types of relationships effectively. The directed hypergraph neural networks learn node representations from these hypergraphs, allowing comprehensive multivariate interaction modeling for anomaly detection. We show through experiments using various evaluation metrics that our proposed method achieves the best scores among the compared methods on two real-world datasets.https://www.tandfonline.com/doi/10.1080/08839514.2025.2538519 |
| spellingShingle | Tae Wook Ha Myoung Ho Kim Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks Applied Artificial Intelligence |
| title | Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks |
| title_full | Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks |
| title_fullStr | Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks |
| title_full_unstemmed | Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks |
| title_short | Multivariate Time Series Anomaly Detection Using Directed Hypergraph Neural Networks |
| title_sort | multivariate time series anomaly detection using directed hypergraph neural networks |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2025.2538519 |
| work_keys_str_mv | AT taewookha multivariatetimeseriesanomalydetectionusingdirectedhypergraphneuralnetworks AT myounghokim multivariatetimeseriesanomalydetectionusingdirectedhypergraphneuralnetworks |