Metraipolis › archive › dc_72155307f6b2

Neural Collapse on Imbalanced Datasets and Open-Set Scenario — arXiv:2611.07753

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07753
License (as archived)
CC0-1.0
Archived
2026-11-06T14:50:42.361Z
SHA-256 of the archived text
dfdc0a775c8e8993ab6f7dcdbe9157257e4bff4300fafdff7a6053824bfdfee3
Stable URL of this page
https://metraipolis.com/documento/dc_72155307f6b2

How to cite

Neural Collapse on Imbalanced Datasets and Open-Set Scenario — arXiv:2611.07753 — arXiv (en), https://arxiv.org/abs/2611.07753 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72155307f6b2 (Metraipolis archive dc_72155307f6b2, sha256 dfdc0a775c8e8993ab6f7dcdbe9157257e4bff4300fafdff7a6053824bfdfee3)
BibTeX
@misc{dc72155307f6b2,
  title = {Neural Collapse on Imbalanced Datasets and Open-Set Scenario — arXiv:2611.07753},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07753},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72155307f6b2; sha256 dfdc0a775c8e8993ab6f7dcdbe9157257e4bff4300fafdff7a6053824bfdfee3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07753. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural collapse (NC) describes the elegant geometric structure that sample features and classifier vectors exhibit when a classification model's loss reaches its minimum. Class imbalance, however, generally distorts standard NC. In this paper, we theoretically reformulate NC on imbalanced datasets and in open-set settings. Our analysis is based on an optimization problem over class-wise averaged losses, rather than the global averaged losses used in prior NC studies. We prove that when class-wise averaged losses attain their minima, standard NC is achieved on balanced or imbalanced datasets, for both cross-entropy (CE) and binary cross-entropy (BCE) losses. We further extend the analysis to an open-set-inspired scenario, where some classes contain no training samples yet are still assigned classifier vectors in the losses. We find that in this scenario, when class-wise averaged losses reach their minima, standard NC still emerges on the known classes with training samples, while the classifier vectors of unknown classes without training samples overlap with each other and become orthogonal to those of the known classes. Finally, we analyze Softmax- and Sigmoid-based contrastive losses re-balanced by inverse sample frequency, proving that at their minima on balanced or imbalanced datasets, sample features of different classes likewise form standard NC.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.07753 — 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 2026-11-06T14:21:42.634Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).