Metraipolis › archive › dc_a55aebbab300

CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning — arXiv:2610.32799

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32799
License (as archived)
CC0-1.0
Archived
2026-10-26T20:12:38.078Z
SHA-256 of the archived text
a337dc2ebf41885a35ebeb9c011ed4bf49e971d649801985ef75150c22a1efbc
Stable URL of this page
https://metraipolis.com/documento/dc_a55aebbab300

How to cite

CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning — arXiv:2610.32799 — arXiv (en), https://arxiv.org/abs/2610.32799 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a55aebbab300 (Metraipolis archive dc_a55aebbab300, sha256 a337dc2ebf41885a35ebeb9c011ed4bf49e971d649801985ef75150c22a1efbc)
BibTeX
@misc{dca55aebbab300,
  title = {CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning — arXiv:2610.32799},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32799},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a55aebbab300; sha256 a337dc2ebf41885a35ebeb9c011ed4bf49e971d649801985ef75150c22a1efbc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32799. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Replay-based Continual Learning mitigates catastrophic forgetting by keeping a buffer of past samples, making buffer composition critical under a fixed memory budget. Recent coreset-based replay methods improve buffer quality using model-derived gradients, losses, or auxiliary optimization, but incur substantial computational overhead as memory is repeatedly updated. We propose CARES, a continual model-optimization-free approach for buffer construction that instead exploits the geometry of a frozen pretrained feature space using class-aware, density-weighted coverage. We evaluate CARES across balanced, imbalanced, and label-noisy streams under online class- and task-incremental settings. On Tiny-ImageNet, CARES is 2.3 to 8.8 times faster than existing coreset-based selectors. Although CARES achieves this speedup using no training signal from the continual learner, it ranks among the state of the art across balanced, imbalanced, and label-noisy streams under online class- and task-incremental settings, outperforming the strongest baseline by up to 7.58 percentage points under class imbalance while also attaining higher average accuracy on Tiny-ImageNet. Code will be released upon publication

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/2610.32799 — 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 2026-10-26T19:49:03.428Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).