Research map / Time series / Long-term forecasting
ReCast: Reliability-aware Codebook-assisted Lightweight Time Series Forecasting
Xiang Ma, Taihua Chen, Pengcheng Wang, Xuemei Li, Caiming Zhang
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 residual path (ablation) | ReCast · Traffic | MSE: 0.435 -> 0.418 | Improved |
| add incremental codebook updating (ablation) | ReCast · Traffic | MSE: 0.553 -> 0.418 | Improved |
| add incremental codebook updating (ablation) | ReCast · ETTm1 | MSE: 0.400 -> 0.371 | Improved |
| add downsampling and random patch sampling (ablation) | ReCast · Weather | MSE: 0.240 -> 0.229 | Improved |
| add reliability-aware scoring weights (ablation) | ReCast · Weather | MSE: 0.249 -> 0.229 | Improved |
| fuse reliability scores with DRO instead of uniform weights (ablation) | ReCast · ETTm1 | MSE: 0.375 -> 0.371 | Improved |
| fuse reliability scores with DRO instead of uniform weights (ablation) | ReCast · Traffic | MSE: 0.424 -> 0.418 | Improved |
| apply ReCast dual-path framework to iTransformer backbone | iTransformer · Traffic | MSE: 0.428 -> 0.420 | Improved |
| apply ReCast dual-path framework to TimesNet backbone | TimesNet · Traffic | MSE: 0.620 -> 0.499 | Improved |
| apply ReCast framework to TimesNet | TimesNet · ETTm1 | MSE: 0.400 -> 0.389 | Improved |
| ReCast vs best baseline TQNet | TQNet · Solar | MSE: 0.209 vs 0.198 | Hurt |
| ReCast vs PatchMLP | PatchMLP · Traffic | MSE: 0.418 vs 0.417 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 1 of 1 shared result
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · 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
- TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting (ICML 2025 · similarity 0.87)
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (NeurIPS 2025 · similarity 0.87)
- Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift (NeurIPS 2025 · similarity 0.86)
- xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories (NeurIPS 2025 · similarity 0.86)
- Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecasting (AAAI 2025 · similarity 0.86)
- Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization (ICML 2025 · similarity 0.86)
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.
