Metraipolis › archive › dc_7bdf7d2b60b6

FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients — arXiv:2608.09250

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.09250
License (as archived): CC0-1.0
Archived: 2026-10-19T08:52:52.049Z
SHA-256 of the archived text: bd7ca6777a6712d7deadf3a5eb0e8e94bb07e9135c8f6698a61b24c57a309f0a
Stable URL of this page: https://metraipolis.com/documento/dc_7bdf7d2b60b6

How to cite

FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients — arXiv:2608.09250 — arXiv (en), https://arxiv.org/abs/2608.09250 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bdf7d2b60b6 (Metraipolis archive dc_7bdf7d2b60b6, sha256 bd7ca6777a6712d7deadf3a5eb0e8e94bb07e9135c8f6698a61b24c57a309f0a)

BibTeX

@misc{dc7bdf7d2b60b6,
  title = {FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients — arXiv:2608.09250},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09250},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bdf7d2b60b6; sha256 bd7ca6777a6712d7deadf3a5eb0e8e94bb07e9135c8f6698a61b24c57a309f0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09250. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per deployment limit is costly. Federated supernet training instead learns one elastic model with differently sized subnetworks, then deploys a suitable one to each device. When client inference budgets differ, however, parameters exclusive to high-cost subnetworks are reachable by fewer clients. We propose FEAST, a federated shared-space training framework that counters this imbalance by jointly training multiple subnetworks within each client's limit. Budget-tailored sub-supernet routing sends only the relevant supernet portion, and sparse aggregation merges the returned parameter slices. The trained supernet directly serves the subnetworks used during federation and supports post-hoc extraction of additional subnetworks without federated retraining. We further show that independently assigning clients' training-data volumes and inference budgets can distort accuracy--inference-cost comparisons in heterogeneous FL simulations, and introduce a one-parameter $\gamma$-allocation protocol to control this coupling. In our experimental setup, the SuperFedNAS and DeepFedNAS supernet training procedures remain near chance at 25M and reach at most $17.09\%$ at $596$M inference MACs; FEAST reaches $71.06\%$ at $596$M, $2.4$ points above the strongest model-heterogeneous weight-sharing baseline at its largest tier. Across CIFAR-100, CINIC-10, and TinyImageNet-200, FEAST achieves the highest population-averaged accuracy among the evaluated weight-sharing methods when each client receives its largest affordable subnetwork. Sub-supernet routing reduces aggregate model-parameter traffic by $6.8\times$ relative to full-supernet transmission.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.DC).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2608.09250 — 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 2026-10-19T08:50:23.789Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).