Metraipolis › archive › dc_cd616b7090f1

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning — arXiv:2611.08383

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08383
License (as archived)
CC0-1.0
Archived
2026-11-06T14:42:55.999Z
SHA-256 of the archived text
15352692338773ef48023a32594c7057c5cefb2c48a12075cf03d0e66eabfc9f
Stable URL of this page
https://metraipolis.com/documento/dc_cd616b7090f1

How to cite

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning — arXiv:2611.08383 — arXiv (en), https://arxiv.org/abs/2611.08383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd616b7090f1 (Metraipolis archive dc_cd616b7090f1, sha256 15352692338773ef48023a32594c7057c5cefb2c48a12075cf03d0e66eabfc9f)
BibTeX
@misc{dccd616b7090f1,
  title = {FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning — arXiv:2611.08383},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08383},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd616b7090f1; sha256 15352692338773ef48023a32594c7057c5cefb2c48a12075cf03d0e66eabfc9f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on the server. In FedReason, the LLM is called every ten rounds. It analyses the weights by running code in a restricted server-side sandbox, sees only the printed results, may score a few candidates on a 500-image proxy set, and submits a short Python aggregation program. The server applies the program until the next call and falls back to FedAvg whenever its output is invalid. Full weight tensors never leave the server. We evaluated FedReason with Claude Opus 5.5 on CIFAR-10 and CIFAR-100 with ResNet-18 under Dirichlet label skew, width-heterogeneous sub-models and Byzantine clients, in 168 runs against 14 baselines. Across 12 paired label-skew runs it beat FedAvg by 1.26 percentage points on average (10 wins), and a control that spends the same per-round proxy budget on choosing among standard rules by 1.08 points. It was the strongest server-side rule on CIFAR-100 but did not beat SCAFFOLD, which changes client training. With three of ten clients malicious, it excluded all sign-flipping clients from the first round and stayed about one point below FLTrust without training a root model. Without proxy feedback, accuracy fell from 73.8% to 38.8% in one seed. A 60-round run cost 0.79 USD in API fees on average.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.08383 — 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 2026-11-06T14:18:42.702Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).