Metraipolis › archive › dc_49e12a56ea75

TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series — arXiv:2610.19557

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19557
License (as archived)
CC0-1.0
Archived
2026-10-15T14:15:36.013Z
SHA-256 of the archived text
d205b103b2cedbf65948a12147297179315e45ea8a502466021b3b6f4e06acac
Stable URL of this page
https://metraipolis.com/documento/dc_49e12a56ea75

How to cite

TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series — arXiv:2610.19557 — arXiv (en), https://arxiv.org/abs/2610.19557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49e12a56ea75 (Metraipolis archive dc_49e12a56ea75, sha256 d205b103b2cedbf65948a12147297179315e45ea8a502466021b3b6f4e06acac)
BibTeX
@misc{dc49e12a56ea75,
  title = {TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series — arXiv:2610.19557},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19557},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49e12a56ea75; sha256 d205b103b2cedbf65948a12147297179315e45ea8a502466021b3b6f4e06acac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19557 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T13:53:35.614Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).