动态重校准让时间序列模型自适应变化模式。
Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting
- 按时间点动态调整模型响应，不靠固定权重
- 在12个数据集上表现媲美大模型，仅用少量参数
- 适合需要实时适应的时序预测场景
真实世界的时间序列中局部时间模式持续变化，而现有深度预测模型普遍使用全局固定的权重矩阵，导致响应僵化，只能取平均表现。本文提出动态模式重校准（DPR），一种与主干网络无关的机制，通过“感知-路由-调制”轻量级流程，对自学习的可变响应模式进行软路由，生成时序感知的调制向量，以残差哈达玛积方式重校准隐藏状态。作为通用适配器，DPR能以极小开销提升多种架构的预测性能；作为独立模型，DPRNet在12个基准测试中达到竞争力表现，验证了动态重校准比宏观参数扩展更有效，解决了时序建模中的通用瓶颈。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。