arXiv：cs.LG· Aditya Radhakrishnan, Maxwell A. Xu, Wanting Mao, Santosh Kumar, Harish Haresamudram, James M. Rehg·· 3 小时前
TEX-MEX：相似度引导的时间序列时序对比学习
TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series
AI 导读
TEX-MEX 是首个将结构相似性与时间相似性统一为单一关系的时间序列对比学习方法，在 PPG、EEG、ECG、加速度计和连续血糖监测上达到 SOTA，优于对比式、重建式、JEPA 及模态专用方法。研究还训练了一个 560K 参数的 PPG 基础模型，在下游基准上取得 SOTA，参数量约为评估中次优单模态预训练 PPG 基础模型的 1/50。该基础模型将以开源开放权重形式发布。
正文
Abstract:Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations reliably preserve meaning in time series, prior methods have relied on two disjoint notions of similarity between windows: structural similarity, which relates windows with similar morphology, and temporal similarity, which relates windows that occur close together in time. We introduce TEX-MEX, to our knowledge the first approach to unify the two into a single relationship. Given a random batch of windows drawn across the dataset, TEX-MEX uses the encoder to identify which windows are structurally similar or dissimilar to each other. It then pulls each window toward the temporally shifted versions of similar windows and pushes it away from those of dissimilar ones, learning what typically accompanies similar windows in time. Across PPG, EEG, ECG, accelerometry, and continuous glucose monitoring, TEX-MEX broadly achieves state-of-the-art performance against contrastive, reconstructive, JEPA-based, and modality-specific approaches, establishing it as a strong general SSL objective. We further train a 560K-parameter PPG foundation model that achieves state-of-the-art performance across a broad range of downstream benchmarks while being roughly 50x smaller than the next-best unimodally pretrained PPG foundation model in our evaluation. We will release this foundation model open-source and open-weight to the community to support future work and practical applications.
| Comments: | 14 pages, 3 figures, 7 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.19557 [cs.LG] |
| (or arXiv:2610.19557v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19557 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aditya Radhakrishnan [view email]
[v1]
Wed, 14 Oct 2026 04:15:12 UTC (332 KB)
来源：arXiv：cs.LG · arxiv.org