时间序列分类的统一对比-生成框架
A Unified Contrastive-Generative Framework for Time Series Classification
AI总结：
提出CoGenT框架，通过联合对比-生成优化统一多变量时间序列自监督学习，克服对比学习对高类内相似性的敏感性及生成方法对大数据集的依赖，在六个数据集上F1显著提升。
摘要：
多变量时间序列的自监督学习（SSL）主要包括两种范式：擅长实例判别的对比方法和对数据分布进行建模的生成方法。尽管两者各自有效，但它们互补的潜力仍未被探索。我们提出了对比生成时间序列框架（CoGenT），这是首个通过联合对比-生成优化来统一这些范式的框架。CoGenT解决了这两种方法的根本局限性：它克服了对比学习对时间数据中高类内相似性的敏感性，同时减少了生成方法对大型数据集的依赖。我们在六个多样化的时间序列数据集上评估了CoGenT。结果显示出一致的改进，与独立的SimCLR和MAE相比，F1分别提高了59.2%和14.27%。我们的分析表明，混合目标在保持判别能力的同时获得了生成鲁棒性。这些发现为时间域中的混合SSL奠定了基础。我们将很快发布代码。
英文摘要：
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.
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。
