Metraipolis › archive › dc_ded7d9fc7d2b
Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise — arXiv:2610.01028
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01028
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:12:30.052Z
- SHA-256 of the archived text
dd6699e2a13ecc3588aa18d4ec5b451232769508abf66a2c970add12af4e0d21- Stable URL of this page
https://metraipolis.com/documento/dc_ded7d9fc7d2b
How to cite
Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise — arXiv:2610.01028 — arXiv (en), https://arxiv.org/abs/2610.01028 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ded7d9fc7d2b (Metraipolis archive dc_ded7d9fc7d2b, sha256 dd6699e2a13ecc3588aa18d4ec5b451232769508abf66a2c970add12af4e0d21)
BibTeX
@misc{dcded7d9fc7d2b,
title = {Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise — arXiv:2610.01028},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01028},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ded7d9fc7d2b; sha256 dd6699e2a13ecc3588aa18d4ec5b451232769508abf66a2c970add12af4e0d21},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01028. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely on shortcut features that fail to generalize across subgroups. A recent line of work mitigates this issue by using loss-based signals to identify informative samples, but these signals can become severely distorted under label noise: mislabeled samples may also incur large losses and contaminate subsequent reweighting or retraining. Despite its practical importance, this intersection remains largely underexplored. We propose POTER, a reweighting framework based on optimal transport that derives sample importance from the transport geometry between the training distribution and a reference distribution constructed from limited validation group annotations. By measuring alignment at the individual-sample level rather than relying on loss, POTER downweights mislabeled or strongly bias-aligned samples while assigning higher importance to samples better aligned with the reference distribution. In addition, POTER requires only a single ERM training stage, moving beyond the retraining paradigm common in recent work. Across standard benchmarks and noisy-label settings, POTER achieves state-of-the-art worst-group accuracy, including cases where label corruption is concentrated within minority subgroups. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.01028 — 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 2026-10-06T10:21:28.147Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).