HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918362306576384 |
|---|---|
| author | Si, Hao Wang, Xiao Zhang, Fan Zhou, Xiaoya Sun, Dengdi Lyu, Wanli Yang, Qingquan Tang, Jin |
| author_facet | Si, Hao Wang, Xiao Zhang, Fan Zhou, Xiaoya Sun, Dengdi Lyu, Wanli Yang, Qingquan Tang, Jin |
| contents | Multivariate time series analysis has long been one of the key research topics in the field of artificial intelligence. However, analyzing complex time series data remains a challenging and unresolved problem due to its high dimensionality, dynamic nature, and complex interactions among variables. Inspired by the strong structural modeling capability of hypergraphs, this paper proposes a novel hypergraph-based time series Transformer backbone network, termed HGTS-Former, to address the multivariate coupling in time series data. Specifically, given the multivariate time series signal, we first normalize and embed each patch into tokens. Then, we adopt the multi-head self-attention to enhance the temporal representation of each patch. The hierarchical hypergraphs are constructed to aggregate the temporal patterns within each channel and fine-grained relations between different variables. After that, we convert the hyperedge into node features through the EdgeToNode module and adopt the feed-forward network to further enhance the output features. Extensive experiments on multiple representative time series analysis tasks and public datasets fully validated the effectiveness of our proposed HGTS-Former. Moreover, we present EAST-ELM640, a large-scale time series dataset for Edge-Localized Mode (ELM) recognition in nuclear fusion, on which we achieve state-of-the-art performance. The source code will be released on https://github.com/Event-AHU/Time_Series_Analysis |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis Si, Hao Wang, Xiao Zhang, Fan Zhou, Xiaoya Sun, Dengdi Lyu, Wanli Yang, Qingquan Tang, Jin Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multivariate time series analysis has long been one of the key research topics in the field of artificial intelligence. However, analyzing complex time series data remains a challenging and unresolved problem due to its high dimensionality, dynamic nature, and complex interactions among variables. Inspired by the strong structural modeling capability of hypergraphs, this paper proposes a novel hypergraph-based time series Transformer backbone network, termed HGTS-Former, to address the multivariate coupling in time series data. Specifically, given the multivariate time series signal, we first normalize and embed each patch into tokens. Then, we adopt the multi-head self-attention to enhance the temporal representation of each patch. The hierarchical hypergraphs are constructed to aggregate the temporal patterns within each channel and fine-grained relations between different variables. After that, we convert the hyperedge into node features through the EdgeToNode module and adopt the feed-forward network to further enhance the output features. Extensive experiments on multiple representative time series analysis tasks and public datasets fully validated the effectiveness of our proposed HGTS-Former. Moreover, we present EAST-ELM640, a large-scale time series dataset for Edge-Localized Mode (ELM) recognition in nuclear fusion, on which we achieve state-of-the-art performance. The source code will be released on https://github.com/Event-AHU/Time_Series_Analysis |
| title | HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.02411 |