Metraipolis › archive › dc_a2f6dd94eca6
Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction — arXiv:2610.41222
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41222
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:51:35.908Z
- SHA-256 of the archived text
8c6c495f6c4164f5348c15690a915f449b363cf27849d33b27ddc52d862c5206- Stable URL of this page
https://metraipolis.com/documento/dc_a2f6dd94eca6
How to cite
Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction — arXiv:2610.41222 — arXiv (en), https://arxiv.org/abs/2610.41222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2f6dd94eca6 (Metraipolis archive dc_a2f6dd94eca6, sha256 8c6c495f6c4164f5348c15690a915f449b363cf27849d33b27ddc52d862c5206)
BibTeX
@misc{dca2f6dd94eca6,
title = {Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction — arXiv:2610.41222},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2f6dd94eca6; sha256 8c6c495f6c4164f5348c15690a915f449b363cf27849d33b27ddc52d862c5206},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In pattern analysis, models trained independently for the same task often develop complementary capabilities through differences in architecture, data, and optimization. Exploiting complementarity while retaining independent deployment is central to collaborative learning. Most methods establish transfer by reducing differences in predictions, relations, or representations between target and collaborator, although these differences also underlie complementarity. This creates a structural trade-off between reducing differences for knowledge exchange and preserving them for complementarity. We therefore propose Corroborative Learning (CL). Each model forms task-driven responses, with cross-group support from its collaborator. Source-excluded reconstruction of response increments from collaborator representations separates fitting and evaluation across disjoint groups and selectively constrains directions by cross-group reconstructability. The process requires no direct output or feature matching or additional inference dependency. Furthermore, with linear reconstruction and fixed collaborator representations, the loss equals a positive semidefinite directional regularizer, constraining less reconstructable directions more strongly. Signal and noise conditions characterize when directional shrinkage reduces response-estimation error. Across six language tasks, 24 models, and 36 pairs, CL improves over capacity-matched independent adaptation on every task, with positive gains across most directed model combinations. Pairwise comparisons show broad advantages over transfer and mutual-learning methods and different gains from complementarity across collaboration rules. Low-label language and vision results support cross-domain applicability. Task-relevant differences can support mutual enhancement without eliminating disagreement. 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/2610.41222 — 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 2026-11-02T04:45:12.876Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).