Metraipolis › archive › dc_f4e000cda62a
Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data — arXiv:2609.14246
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14246
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:17:36.306Z
- SHA-256 of the archived text
848b8e0f0a52fffc2d7d938e70351ae08cb6990ddcf6c3eece916186add2da66- Stable URL of this page
https://metraipolis.com/documento/dc_f4e000cda62a
How to cite
Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data — arXiv:2609.14246 — arXiv (en), https://arxiv.org/abs/2609.14246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4e000cda62a (Metraipolis archive dc_f4e000cda62a, sha256 848b8e0f0a52fffc2d7d938e70351ae08cb6990ddcf6c3eece916186add2da66)
BibTeX
@misc{dcf4e000cda62a,
title = {Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data — arXiv:2609.14246},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14246},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4e000cda62a; sha256 848b8e0f0a52fffc2d7d938e70351ae08cb6990ddcf6c3eece916186add2da66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further affected by unreliable wireless links, as transmission errors may invalidate model updates. To address these challenges, we propose a federated random walk averaging (FedRW) framework, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server. Model parameters are transmitted in packets with retransmission support to improve training quality by mitigating wireless errors along RW paths. Meanwhile, wireless transmission delays hinder the exploration of FedRW. To this end, we formulate a joint optimization problem that integrates learning, RW path selection, and transmission parameter tuning, aiming to minimize the training loss under delay constraints. By deriving an upper bound on the expected convergence of FedRW over unreliable wireless networks, we reduce the problem to a general form agnostic to task type and model architecture. A distributed solution is then proposed, in which the server or clients optimize packet size and maximum number of retransmissions locally, and efficiently select reliable and expandable next-hop nodes via a resilience-aware beam search with dynamic pruning. Simulation results show that FedRW achieves 2.26%-9% higher accuracy than state-of-the-art baselines under high data heterogeneity. Furthermore, the jointly optimized FedRW yields at least 2.78% higher accuracy and faster convergence compared to baselines. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-15 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.14246 — 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 2026-10-15T22:54:12.967Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).