Metraipolis › archive › dc_43ec89a76e55
FedMaJ: Ordinal Meta-Aggregation for Federated Learning Using Majority-Judgment Voting — arXiv:2610.39985
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39985
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:29:18.879Z
- SHA-256 of the archived text
faf794cf0b007dd2d10ce2fba906229fa60505f06bda6da4e2a1ffefa45165c0- Stable URL of this page
https://metraipolis.com/documento/dc_43ec89a76e55
How to cite
FedMaJ: Ordinal Meta-Aggregation for Federated Learning Using Majority-Judgment Voting — arXiv:2610.39985 — arXiv (en), https://arxiv.org/abs/2610.39985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43ec89a76e55 (Metraipolis archive dc_43ec89a76e55, sha256 faf794cf0b007dd2d10ce2fba906229fa60505f06bda6da4e2a1ffefa45165c0)
BibTeX
@misc{dc43ec89a76e55,
title = {FedMaJ: Ordinal Meta-Aggregation for Federated Learning Using Majority-Judgment Voting — arXiv:2610.39985},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39985},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43ec89a76e55; sha256 faf794cf0b007dd2d10ce2fba906229fa60505f06bda6da4e2a1ffefa45165c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated learning traditionally relies on a fixed aggregation rule despite shifting client state and wireless dynamics. We present FedMaJ, a framework that dynamically selects aggregation rules via Majority Judgment voting. During voting rounds, clients evaluate candidate models across performance, resource utilization, channel condition, and fairness metrics. The server adopts the majority-preferred rule and retains it until the next vote, scheduled dynamically based on accuracy trends. Evaluated in over-the-air federated learning with explicit energy and resource cost modeling, synthetic and Fashion-MNIST experiments show that FedMaJ achieves competitive learning performance and superior aggregation-influence fairness. Under extreme-evaluation perturbations, Majority Judgment yields significantly more stable rule selections than mean-based scoring, establishing ordinal voting as a robust control layer for adaptive aggregation. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.NI, nuovi lavori del giorno). Categorie arXiv: Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2610.39985 — 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 2026-11-01T02:13:13.506Z dalla pagina https://arxiv.org/list/cs.NI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).