Metraipolis › archive › dc_4586fe494e7f
Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning — arXiv:2608.21147
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21147
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:31:12.841Z
- SHA-256 of the archived text
12c8f03360c3ea9c19157e62a3e5f04f607cfeb3ea4d89916a8f2360f4afd7a0- Stable URL of this page
https://metraipolis.com/documento/dc_4586fe494e7f
How to cite
Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning — arXiv:2608.21147 — arXiv (en), https://arxiv.org/abs/2608.21147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4586fe494e7f (Metraipolis archive dc_4586fe494e7f, sha256 12c8f03360c3ea9c19157e62a3e5f04f607cfeb3ea4d89916a8f2360f4afd7a0)
BibTeX
@misc{dc4586fe494e7f,
title = {Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning — arXiv:2608.21147},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21147},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4586fe494e7f; sha256 12c8f03360c3ea9c19157e62a3e5f04f607cfeb3ea4d89916a8f2360f4afd7a0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The cyclic structure of physiological processes offers a natural prior for self-supervised representation learning, and the cardiac cycle provides a particularly well-defined setting in which to exploit it. We derive a phase-equivariant self-supervised objective and introduce Winder, a joint-embedding architecture that organises representations into phase-invariant coordinates and phase-rotating harmonic subspaces. Its transport operator is fixed and closed-form, derived from the cycle's geometry rather than learned, and adds no parameters. Evaluated on PTB-XL under a frozen linear-probe protocol, Winder attains diagnostic accuracy within the range reported by state-of-the-art self-supervised methods at a ~1 M parameter footprint, while exhibiting phase-equivariant latent geometry. These findings demonstrate that explicitly encoding cardiac-phase symmetry can preserve diagnostically useful information while yielding a latent geometry that is legible, parameter-efficient, and directly tied to a measurable physiological quantity. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.21147 — 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 2026-10-18T10:27:55.956Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).