Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.06310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915989525889024 |
|---|---|
| author | Zhong, Siru Meng, Zhao Fu, Haohuan Li, Haoyang Wen, Qingsong Liang, Yuxuan |
| author_facet | Zhong, Siru Meng, Zhao Fu, Haohuan Li, Haoyang Wen, Qingsong Liang, Yuxuan |
| contents | Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied uniformly to all temporal tokens. This creates a static pattern response: models settle into a compromised average, unable to adapt to changing local dynamics. We introduce Dynamic Pattern Recalibration (DPR), a backbone-agnostic mechanism that resolves this via token-level recalibration. Through a lightweight "Perceive-Route-Modulate" pipeline, DPR computes a soft-routing distribution over a learned basis of adaptive response patterns, generating a time-aware modulation vector that recalibrates hidden states via a residual Hadamard product. As a backbone-agnostic adapter, DPR enhances forecasting across diverse architectures with minimal overhead, confirming it addresses a general bottleneck. As a minimalist standalone model, DPRNet achieves competitive performance across 12 benchmarks, validating dynamic recalibration against macroscopic parameter scaling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06310 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting Zhong, Siru Meng, Zhao Fu, Haohuan Li, Haoyang Wen, Qingsong Liang, Yuxuan Machine Learning Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied uniformly to all temporal tokens. This creates a static pattern response: models settle into a compromised average, unable to adapt to changing local dynamics. We introduce Dynamic Pattern Recalibration (DPR), a backbone-agnostic mechanism that resolves this via token-level recalibration. Through a lightweight "Perceive-Route-Modulate" pipeline, DPR computes a soft-routing distribution over a learned basis of adaptive response patterns, generating a time-aware modulation vector that recalibrates hidden states via a residual Hadamard product. As a backbone-agnostic adapter, DPR enhances forecasting across diverse architectures with minimal overhead, confirming it addresses a general bottleneck. As a minimalist standalone model, DPRNet achieves competitive performance across 12 benchmarks, validating dynamic recalibration against macroscopic parameter scaling. |
| title | Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.06310 |