Metraipolis › archive › dc_a11f331f5dd5

Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data — arXiv:2610.32039

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32039
License (as archived)
CC0-1.0
Archived
2026-10-26T19:51:37.790Z
SHA-256 of the archived text
f30ae25f7329e5d893247e0d1bda0403f71fec330e43767cc76921db9635be6b
Stable URL of this page
https://metraipolis.com/documento/dc_a11f331f5dd5

How to cite

Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data — arXiv:2610.32039 — arXiv (en), https://arxiv.org/abs/2610.32039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a11f331f5dd5 (Metraipolis archive dc_a11f331f5dd5, sha256 f30ae25f7329e5d893247e0d1bda0403f71fec330e43767cc76921db9635be6b)
BibTeX
@misc{dca11f331f5dd5,
  title = {Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data — arXiv:2610.32039},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a11f331f5dd5; sha256 f30ae25f7329e5d893247e0d1bda0403f71fec330e43767cc76921db9635be6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Supervised contrastive learning and its balanced variants have demonstrated their effectiveness for representation learning under long-tailed distributions. However, although prior analyses suggest that their optimal representations may exhibit a regular simplex geometry, whether such a geometry is indeed exhibited remains insufficiently understood. In this work, we present a theoretical framework for these objectives that characterizes whether a regular simplex is formed at the optimum. By applying this to representative objectives, we show that these objectives fail to form a regular simplex at the optimum because they remain dependent on the number of samples per class. Motivated by this analysis, we introduce structural balancing that can be applied to contrastive objectives, and propose a fully balanced contrastive objective that provably forms a regular simplex geometry at its optimum. Both theoretical and empirical results demonstrate that the proposed method yields a more balanced representation space and improves performance on long-tailed recognition and transfer learning tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.32039 — 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 2026-10-26T19:45:33.378Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).