Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting

TL;DR

The paper introduces DPR, a flexible recalibration mechanism for time series forecasting that adapts local patterns dynamically, improving performance across various models and benchmarks.

Contribution

DPR provides a novel token-level recalibration approach that enhances existing models and introduces a minimalist standalone model, addressing a key limitation in static pattern response.

Findings

DPR improves forecasting accuracy across diverse architectures.

DPRNet achieves competitive results on 12 benchmarks.

Dynamic recalibration outperforms static models in adapting to local pattern shifts.

Abstract

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.