提出多尺度动态归一化框架，提升分布漂移下的时序预测精度。
Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts
- 基于多尺度统计预测与自适应融合，实现灵活归一化与反归一化。
- 在5个主流模型上验证，平均性能提升显著，优于现有归一化方法。
- 适合长期时序预测中分布变化剧烈的场景，如金融、气象建模。
复杂的分布漂移是实现准确长期时序预测的主要障碍。已有工作尝试捕捉分布特性并提出自适应归一化方法以缓解分布漂移影响，但忽略了不同尺度下分布动态的复杂性及其归一化映射关系的演化特性。为此，我们提出一种新型、与模型无关的演化多尺度归一化（EvoMSN）框架，以应对分布漂移问题。该框架基于多尺度统计预测模块和自适应融合机制，实现灵活的归一化与反归一化。设计了演化优化策略，协同更新预测模型与统计预测模块，以追踪不断变化的分布。我们在基准数据集上评估了 EvoMSN 对五种主流预测方法的性能提升效果，并展示了其相较于现有先进归一化方法与在线学习方法的优越性。代码已公开于 https://github.com/qindalin/EvoMSN。
原文摘要 · Abstract (English)
Complex distribution shifts are the main obstacle to achieving accurate long-term time series forecasting. Several efforts have been conducted to capture the distribution characteristics and propose adaptive normalization techniques to alleviate the influence of distribution shifts. However, these methods neglect the intricate distribution dynamics observed from various scales and the evolving functions of distribution dynamics and normalized mapping relationships. To this end, we propose a novel model-agnostic Evolving Multi-Scale Normalization (EvoMSN) framework to tackle the distribution shift problem. Flexible normalization and denormalization are proposed based on the multi-scale statistics prediction module and adaptive ensembling. An evolving optimization strategy is designed to update the forecasting model and statistics prediction module collaboratively to track the shifting distributions. We evaluate the effectiveness of EvoMSN in improving the performance of five mainstream forecasting methods on benchmark datasets and also show its superiority compared to existing advanced normalization and online learning approaches. The code is publicly available at https://github.com/qindalin/EvoMSN.
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。