Metraipolis › archive › dc_efb5e1aee8b7

ParaBlock++: Communication-Computation Parallel Blockwise Hierarchical Federated Learning — arXiv:2611.01040

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01040
License (as archived)
CC0-1.0
Archived
2026-11-03T11:20:51.972Z
SHA-256 of the archived text
23f0a16e75c573ac63cb593b47415691c8251c5162000d14e4b37c5b826b9451
Stable URL of this page
https://metraipolis.com/documento/dc_efb5e1aee8b7

How to cite

ParaBlock++: Communication-Computation Parallel Blockwise Hierarchical Federated Learning — arXiv:2611.01040 — arXiv (en), https://arxiv.org/abs/2611.01040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efb5e1aee8b7 (Metraipolis archive dc_efb5e1aee8b7, sha256 23f0a16e75c573ac63cb593b47415691c8251c5162000d14e4b37c5b826b9451)
BibTeX
@misc{dcefb5e1aee8b7,
  title = {ParaBlock++: Communication-Computation Parallel Blockwise Hierarchical Federated Learning — arXiv:2611.01040},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01040},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efb5e1aee8b7; sha256 23f0a16e75c573ac63cb593b47415691c8251c5162000d14e4b37c5b826b9451},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In the emerging 6G paradigm, where AI-driven services operate over decentralized and resource-constrained infrastructures, the convergence of distributed learning algorithms remains a significant challenge. This paper introduces $\mathrm{ParaBlock}$++, a low Earth orbit (LEO) satellite-assisted hierarchical federated learning (HFL) framework, enabling resource-limited terrestrial clients to collaboratively engage in federated learning (FL) via ground-satellite links (GSLs) supported by LEO satellite megaconstellations. Within this architecture, LEO satellites serve multiple roles: as edge servers aggregating and broadcasting models, as clients accelerating training, and as high-throughput relays managing inter-satellite routing through inter-satellite links (ISLs). Departing from conventional synchronous Jacobian-type updates, $\mathrm{ParaBlock}$++ employs asynchronous BCD-type updates to enhance convergence speed. We provide theoretical convergence guarantees for convex, strongly convex, and non-convex objectives, and formulate optimization problems to determine optimal cluster resource allocation and model partitioning for minimizing global training latency. Experimental evaluations demonstrate that $\mathrm{ParaBlock}$++ achieves faster initial convergence and comparable final performance for deep neural networks (DNNs) such as ResNet-18, offering promising directions for federated learning across geographically remote areas enabled by 6G technologies, but much less global rounds and communication cost.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01040 — 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 2026-11-03T11:02:37.490Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).