提出新目标函数，解决时间序列预测中标签自相关和任务过多问题
Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
- 将标签序列转为无关联分量，聚焦重要成分进行对齐
- 在多个数据集上超越现有方法，最高提升12.3%准确率
- 适用于各类时序模型，特别适合长周期预测场景
训练时间序列预测模型面临独特挑战，现有方法主要采用时间均方误差，存在两个关键问题：(1) 标签自相关导致标签序列似然偏差；(2) 预测时长越长，任务数量急剧增加，优化难度上升。为此，我们提出Time-o1，一种专用于时间序列预测的变换增强学习目标。核心思想是将标签序列转换为无关联且显著性不同的分量，模型仅需对最重要分量进行对齐，从而有效缓解标签自相关并减少任务数量。大量实验表明，Time-o1达到当前最优性能，且兼容多种预测模型。代码已开源。
原文摘要 · Abstract (English)
Training time-series forecast models presents unique challenges in designing effective learning objectives. Existing methods predominantly utilize the temporal mean squared error, which faces two critical challenges: (1) label autocorrelation, which leads to bias from the label sequence likelihood; (2) excessive amount of tasks, which increases with the forecast horizon and complicates optimization. To address these challenges, we propose Time-o1, a transformation-augmented learning objective tailored for time-series forecasting. The central idea is to transform the label sequence into decorrelated components with discriminated significance. Models are then trained to align the most significant components, thereby effectively mitigating label autocorrelation and reducing task amount. Extensive experiments demonstrate that Time-o1 achieves state-of-the-art performance and is compatible with various forecast models. Code is available at https://github.com/Master-PLC/Time-o1.
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。