FedReason：让大语言模型作为权重空间元聚合器应对异构联邦学习
FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning
AI 导读
FedReason 让 LLM 在联邦学习服务器端每十轮调用一次，通过受限沙箱分析客户端权重并生成 Python 聚合程序，全程无需服务器训练，权重张量不出服务器。
正文 · 原文
Abstract: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.
| Comments: | Ali Mohammadi Ruzbahani (corresponding) |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.08383 [cs.CR] |
| (or arXiv:2611.08383v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08383 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ali Mohammadi Ruzbahani [view email]
[v1]
Thu, 5 Nov 2026 18:00:58 UTC (433 KB)
来源：arXiv cs.AI · arxiv.org