Research map / Time series / Long-term forecasting
DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting
Zhiding Liu, Jiqian Yang, Qingyang Mao, Yuze Zhao, Mingyue Cheng, Zhi Li, Qi Liu, Enhong Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DisenTS mixture of forecasters | DLinear · Solar (horizon 96) | MSE: 0.226 -> 0.201 | Improved |
| add DisenTS mixture of forecasters | DLinear · Weather (horizon 96) | MSE: 0.176 -> 0.158 | Improved |
| add DisenTS mixture of forecasters | DLinear · Traffic (horizon 96) | MSE: 0.411 -> 0.386 | Improved |
| add DisenTS mixture of forecasters | PatchTST · Traffic (horizon 96) | MSE: 0.395 -> 0.365 | Improved |
| add DisenTS mixture of forecasters | PatchTST · Exchange (horizon 336) | MSE: 0.343 -> 0.350 | Hurt |
| add DisenTS mixture of forecasters | ConvTimeNet · Exchange (horizon 720) | MSE: 0.859 -> 0.895 | Hurt |
| add DisenTS mixture of forecasters | DLinear · long-term benchmarks (36 settings) | MAE: 28 out of 36 | Improved |
| add DisenTS mixture of forecasters | SparseTSF and PatchTST · long-term benchmarks | MSE: 2.8% and 2.3% | Improved |
| add DisenTS mixture of forecasters | iTransformer, CARD, TimesNet, TimeMixer · PEMS short-term (lookback 96) | MSE: nearly 20% | Improved |
| add DisenTS mixture of forecasters | iTransformer · Electricity avg (channel-dependent) | MSE: 0.166 -> 0.161 | Improved |
| add DisenTS mixture of forecasters | TimesNet · Traffic avg (channel-dependent) | MSE: 0.624 -> 0.582 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 2 of 2 shared results
- SparseTSF — SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters (ICML 2024) · better on 2 of 2 shared results
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 2 of 2 shared results
- TimeMixer — TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (ICLR 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (NeurIPS 2025 · similarity 0.89)
- From Similarity to Superiority: Channel Clustering for Time Series Forecasting (NeurIPS 2024 · similarity 0.88)
- Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling (ICML 2024 · similarity 0.88)
- Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting (AAAI 2025 · similarity 0.88)
- OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain (NeurIPS 2025 · similarity 0.88)
- HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
