Metraipolis › archive › dc_3459fbefd833
Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication — arXiv:2608.15256
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15256
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:13:32.820Z
- SHA-256 of the archived text
6ac140bb2371cddfb7c68dfddc1b52c21e28f70a2736d291ddb0364acb913aae- Stable URL of this page
https://metraipolis.com/documento/dc_3459fbefd833
How to cite
Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication — arXiv:2608.15256 — arXiv (en), https://arxiv.org/abs/2608.15256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3459fbefd833 (Metraipolis archive dc_3459fbefd833, sha256 6ac140bb2371cddfb7c68dfddc1b52c21e28f70a2736d291ddb0364acb913aae)
BibTeX
@misc{dc3459fbefd833,
title = {Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication — arXiv:2608.15256},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15256},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3459fbefd833; sha256 6ac140bb2371cddfb7c68dfddc1b52c21e28f70a2736d291ddb0364acb913aae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing topology-agnostic aggregation into heterogeneous, multi-task environments creates a fundamental bottleneck: it drives negative transfer and overconsensus bias (OCB). This paper introduces a personalized DSC framework that cuts off this cross-task interference. At the node level, a policy-driven multi-path routing mechanism separates task-specific features from shared representations to preserve local fidelity. Across the network, we deploy a "communicationwhile- aggregation" protocol. It calibrates a column-stochastic consensus matrix using task affinities. This limits the system to absorbing complementary knowledge while actively blocking mismatched parameter updates. To bound the convergence, we derive a unified Lyapunov drift analysis. We reveal a strict Ushaped trade-off: deeper topological mixing reduces variance but amplifies structural OCB. Resolving this tension yields a closed-form expression for the optimal aggregation depth. We evaluate the proposed framework on NYU-v2, where the results reveal a clear trade-off between insufficient aggregation and excessive topological mixing. At the analytically derived optimal aggregation depth, our method achieves a 4.77% global relative improvement over the no-aggregation baseline and outperforms decentralized FedAvg, FedAMP, and heuristic max aggregation. We further evaluate the framework on Taskonomy and imperfect wireless links to examine the effects of network-size variation and wireless-link reliability. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.15256 — 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 2026-10-18T16:29:13.782Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).