TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
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_ | 1866909812625768448 |
|---|---|
| author | Ma, Xiaowen Ge, Shuning Yang, Fan Li, Xiangyu Chen, Yun Ma, Mengting Zhang, Wei Liu, Zhipeng |
| author_facet | Ma, Xiaowen Ge, Shuning Yang, Fan Li, Xiangyu Chen, Yun Ma, Mengting Zhang, Wei Liu, Zhipeng |
| contents | Transformer-based architectures dominate time series modeling by enabling global attention over all timestamps, yet their rigid 'one-size-fits-all' context aggregation fails to address two critical challenges in real-world data: (1) inherent lag effects, where the relevance of historical timestamps to a query varies dynamically; (2) anomalous segments, which introduce noisy signals that degrade forecasting accuracy. To resolve these problems, we propose the Temporal Mix of Experts (TMOE), a novel attention-level mechanism that reimagines key-value (K-V) pairs as local experts (each specialized in a distinct temporal context) and performs adaptive expert selection for each query via localized filtering of irrelevant timestamps. Complementing this local adaptation, a shared global expert preserves the Transformer's strength in capturing long-range dependencies. We then replace the vanilla attention mechanism in popular time-series Transformer frameworks (i.e., PatchTST and Timer) with TMOE, without extra structural modifications, yielding our specific version TimeExpert and general version TimeExpert-G. Extensive experiments on seven real-world long-term forecasting benchmarks demonstrate that TimeExpert and TimeExpert-G outperform state-of-the-art methods. Code is available at https://github.com/xwmaxwma/TimeExpert. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts Ma, Xiaowen Ge, Shuning Yang, Fan Li, Xiangyu Chen, Yun Ma, Mengting Zhang, Wei Liu, Zhipeng Machine Learning Transformer-based architectures dominate time series modeling by enabling global attention over all timestamps, yet their rigid 'one-size-fits-all' context aggregation fails to address two critical challenges in real-world data: (1) inherent lag effects, where the relevance of historical timestamps to a query varies dynamically; (2) anomalous segments, which introduce noisy signals that degrade forecasting accuracy. To resolve these problems, we propose the Temporal Mix of Experts (TMOE), a novel attention-level mechanism that reimagines key-value (K-V) pairs as local experts (each specialized in a distinct temporal context) and performs adaptive expert selection for each query via localized filtering of irrelevant timestamps. Complementing this local adaptation, a shared global expert preserves the Transformer's strength in capturing long-range dependencies. We then replace the vanilla attention mechanism in popular time-series Transformer frameworks (i.e., PatchTST and Timer) with TMOE, without extra structural modifications, yielding our specific version TimeExpert and general version TimeExpert-G. Extensive experiments on seven real-world long-term forecasting benchmarks demonstrate that TimeExpert and TimeExpert-G outperform state-of-the-art methods. Code is available at https://github.com/xwmaxwma/TimeExpert. |
| title | TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.23145 |