提出统一对比与生成学习的时序分类框架，提升模型性能与鲁棒性。
A Unified Contrastive-Generative Framework for Time Series Classification
- 联合优化对比与生成目标，融合两种自监督学习优势。
- 在6个数据集上相比SimCLR和MAE分别提升59.2%和14.27% F1分数。
- 适合需要低标注依赖与高泛化能力的时序数据分析场景。
多变量时间序列的自监督学习主要分为两类：对比方法擅长实例判别，生成方法能建模数据分布。尽管各自有效，但其互补潜力尚未挖掘。本文提出首个统一这两种范式的框架——对比生成时间序列框架（CoGenT），通过联合对比-生成优化实现融合。CoGenT克服了对比学习对时序数据类内相似性敏感的问题，同时降低了生成方法对大规模数据的依赖。我们在六个多样化的时间序列数据集上评估了该框架，结果表明性能持续提升，相比独立的SimCLR和MAE分别获得最高59.2%和14.27%的F1分数提升。分析显示，混合目标在保持判别力的同时增强了生成稳健性。这些发现为时序领域混合自监督学习奠定了基础。代码将尽快公开。
原文摘要 · Abstract (English)
Self-supervised learning (SSL) for multivariate time series mainly includes two paradigms: contrastive methods that excel at instance discrimination and generative approaches that model data distributions. While effective individually, their complementary potential remains unexplored. We propose a Contrastive Generative Time series framework (CoGenT), the first framework to unify these paradigms through joint contrastive-generative optimization. CoGenT addresses fundamental limitations of both approaches: it overcomes contrastive learning's sensitivity to high intra-class similarity in temporal data while reducing generative methods' dependence on large datasets. We evaluate CoGenT on six diverse time series datasets. The results show consistent improvements, with up to 59.2% and 14.27% F1 gains over standalone SimCLR and MAE, respectively. Our analysis reveals that the hybrid objective preserves discriminative power while acquiring generative robustness. These findings establish a foundation for hybrid SSL in temporal domains. We will release the code shortly.
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。