用自监督方法重构时间序列标签，提升模型泛化能力
Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
- 通过重建网络生成伪标签，实现自监督重标注
- 在11个真实数据集上提升多种主干模型性能
- 适合需要提升泛化性的时序预测研究者
时间序列预测（TSF）在多个领域至关重要，但现有模型高度依赖高质量数据，未能充分利用所有可用数据。本文提出一种新颖的自监督重标注方法，通过构建候选数据集，在简单重建网络优化过程中，将中间结果作为伪标签，实现自监督学习，从而提升任意预测器的泛化能力。引入自适应掩码自校正（SCAM）机制，丢弃过拟合部分，用重建生成的伪标签替代；同时采用谱范数正则化（SNR），从损失景观角度进一步抑制过拟合。在11个真实世界数据集上的实验表明，SCAM能持续提升多种主干模型的性能。该工作为数据集构建和基于自监督学习增强时序预测模型泛化性提供了新视角。代码已开源：https://github.com/SuDIS-ZJU/SCAM。
原文摘要 · Abstract (English)
Time Series Forecasting (TSF) is a crucial task in various domains, yet existing TSF models rely heavily on high-quality data and insufficiently exploit all available data. This paper explores a novel self-supervised approach to re-label time series datasets by inherently constructing candidate datasets. During the optimization of a simple reconstruction network, intermediates are used as pseudo labels in a self-supervised paradigm, improving generalization for any predictor. We introduce the Self-Correction with Adaptive Mask (SCAM), which discards overfitted components and selectively replaces them with pseudo labels generated from reconstructions. Additionally, we incorporate Spectral Norm Regularization (SNR) to further suppress overfitting from a loss landscape perspective. Our experiments on eleven real-world datasets demonstrate that SCAM consistently improves the performance of various backbone models. This work offers a new perspective on constructing datasets and enhancing the generalization of TSF models through self-supervised learning. The code is available at https://github.com/SuDIS-ZJU/SCAM.
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。