analiza aiqbench
This research introduces Winder, a parameter-efficient self-supervised learning architecture that explicitly encodes the cyclic symmetry of cardiac cycles to improve diagnostic accuracy on ECG data. By leveraging closed-form transport operators derived from physiological geometry rather than learned parameters, the method achieves state-of-the-art performance with only ~1M parameters while maintaining interpretable latent spaces. The work demonstrates a novel application of equivariant learning principles to biomedical signal processing, bridging mathematical symmetry constraints with practical medical AI tasks.
Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning
arXiv:2608.21147v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2608.21147 [cs.LG]
(or arXiv:2608.21147v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.21147 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 224 cuvinte
Subiecte conexe
Echo-POSED: Geometric Self-Distillation for Echocardiography Guidance
arXiv · 3 iun. 2026
XtalPi Holdings Limited: XtalPi Holdings Announces 2026 Interim Results
finanznachrichten.de · 19 aug. 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026
Cross-Temperature Defect Identification in Atomistic Simulations via Multi-Level Domain Alignment
arXiv · 25 aug. 2026