Metraipolis › archive › dc_aa08da9d62fe

FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices — arXiv:2609.06106

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06106
License (as archived)
CC0-1.0
Archived
2026-10-16T13:07:25.269Z
SHA-256 of the archived text
b6dcc30cb2f50e56159aba0ded43300aebd75613228cdc9631a1e2879c1875f0
Stable URL of this page
https://metraipolis.com/documento/dc_aa08da9d62fe

How to cite

FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices — arXiv:2609.06106 — arXiv (en), https://arxiv.org/abs/2609.06106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa08da9d62fe (Metraipolis archive dc_aa08da9d62fe, sha256 b6dcc30cb2f50e56159aba0ded43300aebd75613228cdc9631a1e2879c1875f0)
BibTeX
@misc{dcaa08da9d62fe,
  title = {FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices — arXiv:2609.06106},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06106},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa08da9d62fe; sha256 b6dcc30cb2f50e56159aba0ded43300aebd75613228cdc9631a1e2879c1875f0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL methods typically bind training to a small predefined menu of model configurations, which limits architectural coverage. To address this bottleneck, we introduce Federated Adaptive Network Search (FANS), a hypernetwork-based framework that learns a shared architecture space rather than a fixed set of client models. To optimize this shared space efficiently, we propose the Federated Parallel Scaling (FPS) algorithm, which jointly trains multiple sampled subnetworks in parallel with self-distillation so that larger sampled subnetworks can supervise smaller ones during local updates. We evaluate FANS on CIFAR-10, CIFAR-100, and MNLI using ResNet-18, DenseNet-121, and BERT-base, respectively. Across all benchmarks, FANS expands the feasible subnetwork pool by orders of magnitude (e.g., 4,680 candidates for ResNet-18 vs. 4 in existing methods) and improves the average accuracy-efficiency trade-off relative to representative HFL baselines. Device heterogeneity is emulated through resource tiers, and evaluation covers accuracy, parameter count, and MACs.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.DC).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.06106 — 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 2026-10-16T13:02:21.608Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).