三阶段学习解锁简单模型在长期时间序列预测中的强大性能
Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting
AI总结：
本文提出STAIR方法，通过三阶段学习提升简单时间映射模型性能，引入共享到个体微调和alpha-RevIN以缓解通道独立性和归一化先验限制，实验证明其在长期预测中的有效性。
摘要：
近期研究显示，简单的线性模型和MLP基预测器在长期时间序列预测中可取得强性能，无需更复杂的架构。然而，许多竞争基线仍依赖结构先验如频域建模、显式分解、多尺度混合或复杂的跨变量交互模块，而较少关注如何训练和组织简单的时序映射。本文提出STAIR（Stagewise Temporal Adaptation via Individualization and Residual Learning），一种针对长期时间序列预测的训练范式，旨在解锁简单时序映射模型的潜力而不引入复杂架构模块。STAIR将预测能力分解为三个渐进阶段：首先通过共享时序映射学习变量间的共同时序动态，然后通过通道级微调适应共享模型以捕捉变量特定模式，最后通过残差学习补充骨干网络以跨变量信息。我们进一步引入Shared-to-Individual Fine-tuning和alpha-RevIN以缓解严格通道独立性和标准RevIN引起的过度强归一化先验限制。此设计逐步增加建模灵活性，同时在主要实验中保持核心时序预测器为浅层MLP，线性变体分别分析。在九个长期预测基准测试中，STAIR与最近的强基线匹配或超越，同时保持简单的时序骨干，为长期时间序列预测提供了简洁有效的建模视角。
英文摘要：
Recent studies on long-term time series forecasting have shown that simple linear models and MLP-based predictors can achieve strong performance without increasingly complex architectures. However, many competitive baselines still rely on structural priors such as frequency-domain modeling, explicit decomposition, multi-scale mixing, or sophisticated cross-variable interaction modules, while paying less attention to how simple temporal mappings should be trained and organized. In this paper, we propose STAIR, short for Stagewise Temporal Adaptation via Individualization and Residual Learning, a training paradigm for long-term time series forecasting that aims to unlock the capacity of simple temporal mapping models without introducing complex architectural modules. STAIR decomposes forecasting ability into three progressive stages: it first learns common temporal dynamics across variables through a shared temporal mapping, then adapts the shared model to each variable via channel-wise fine-tuning to capture variable-specific patterns, and finally complements the backbone with cross-variable information through residual learning. We further introduce Shared-to-Individual Fine-tuning and alpha-RevIN to mitigate the limitations of strict channel independence and the overly strong normalization prior induced by standard RevIN. This design gradually increases modeling flexibility while keeping the core temporal predictor as a shallow MLP in the main experiments, with linear variants analyzed separately. Experiments on nine long-term forecasting benchmarks show that STAIR matches or outperforms recent strong baselines while preserving a simple temporal backbone, providing a concise and effective modeling perspective for long-term time series forecasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
