Metraipolis › archive › dc_366d43944f6c

A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints — arXiv:2608.26493

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26493
License (as archived): CC0-1.0
Archived: 2026-10-17T16:09:31.822Z
SHA-256 of the archived text: 7a57cdbf4a04a1d13090c5ca85d453f4cae6d33a42f00bc7deb26a51dd3592f6
Stable URL of this page: https://metraipolis.com/documento/dc_366d43944f6c

How to cite

A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints — arXiv:2608.26493 — arXiv (en), https://arxiv.org/abs/2608.26493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_366d43944f6c (Metraipolis archive dc_366d43944f6c, sha256 7a57cdbf4a04a1d13090c5ca85d453f4cae6d33a42f00bc7deb26a51dd3592f6)

BibTeX

@misc{dc366d43944f6c,
  title = {A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints — arXiv:2608.26493},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26493},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_366d43944f6c; sha256 7a57cdbf4a04a1d13090c5ca85d453f4cae6d33a42f00bc7deb26a51dd3592f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decentralized learning systems aim to collaboratively train models across multiple clients without relying on a central coordinator. While decentralization improves scalability, privacy, and robustness, it also exacerbates three fundamental challenges: statistical heterogeneity across clients, fairness in client-level performance, and stringent communication constraints. This raises a natural question: \emph{how fair can decentralized learning be under limited communication?} We address this question by presenting a unified framework for decentralized learning under communication constraints, bringing together graph-based personalization, agnostic fairness, and compressed event-triggered communication. Specifically, we propose a new algorithm DMFL-SQ, a decentralized multi-task learning algorithm that couples personalized model training over a communication graph with an agnostic mixture fairness objective, while reducing communication through sparsification, quantization, and event-triggered synchronization. We establish convergence guarantees for general non-convex objectives and show that DMFL-SQ achieves an $\mathcal{O}(T^{-1/2})$ rate in expected squared Moreau-envelope stationarity despite sparse, quantized, and event-triggered communication. We further derive PAC-Bayes generalization guarantees for the fairness-aware mixture objective. Experiments on CIFAR-10 and the real heterogeneous MUSMET EEG dataset demonstrate that DMFL-SQ substantially reduces communication while maintaining predictive performance and improving fairness across clients. Together, our theoretical and empirical results show that personalization, fairness, and communication efficiency can be jointly achieved in decentralized learning while preserving the dominant convergence rate.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.26493 — 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 2026-10-17T15:34:49.902Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).