Metraipolis › archive › dc_cc9d92dbc159
FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks — arXiv:2609.26377
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26377
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:47:10.356Z
- SHA-256 of the archived text
865cb9f308b1a481a0d4c9597b03740c6c0231c643d142eb9afaffd59e889168- Stable URL of this page
https://metraipolis.com/documento/dc_cc9d92dbc159
How to cite
FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks — arXiv:2609.26377 — arXiv (en), https://arxiv.org/abs/2609.26377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc9d92dbc159 (Metraipolis archive dc_cc9d92dbc159, sha256 865cb9f308b1a481a0d4c9597b03740c6c0231c643d142eb9afaffd59e889168)
BibTeX
@misc{dccc9d92dbc159,
title = {FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks — arXiv:2609.26377},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26377},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc9d92dbc159; sha256 865cb9f308b1a481a0d4c9597b03740c6c0231c643d142eb9afaffd59e889168},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing a fairness--robustness conflict. We propose FairMean to manage this conflict. FairMean weights client gradients using a bounded, nondecreasing function of local loss. The increasing weights prioritize high-loss clients to promote fairness, while the upper bound prevents excessive loss-induced amplification of poisoned-client gradients. In the absence of label poisoning, we show that minimizing the FairMean objective is more conducive to solution fairness than minimizing the standard average-loss objective. Under label poisoning, we establish an average-stationarity bound whose attack-dependent term is proportional to the square of the poisoned-client fraction. Experiments show that FairMean promotes fairness by reducing accuracy variance while improving worst-client accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.26377 — 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 2026-10-08T13:18:38.310Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).