自动选择联邦学习聚合策略，提升模型鲁棒性与适应性。
Automating aggregation strategy selection in federated learning
- 用大语言模型或遗传搜索自动选最优聚合策略
- 在非独立同分布数据下性能更稳定，减少人工调参
- 适合需要快速部署、缺乏经验的联邦学习使用者
联邦学习可在不集中数据的前提下实现协同建模，但其效果高度依赖聚合策略的选择。该选择复杂，因数据集、异构程度和算力约束差异而表现迥异。本文提出一个端到端框架，自动、高效且自适应地选择联邦学习中的聚合策略。框架包含两种模式：单次试验模式下，大语言模型基于用户输入或自动检测的数据特征推断合适策略；多轮试验模式下，轻量级遗传搜索在预算受限时高效探索策略空间。大量实验表明，该方法在多样化数据集上提升了非独立同分布条件下的鲁棒性与泛化能力，显著降低对人工干预的需求。本工作通过自动化关键设计决策，推动了更易用、更自适应的联邦学习发展。
原文摘要 · Abstract (English)
Federated Learning enables collaborative model training without centralising data, but its effectiveness varies with the selection of the aggregation strategy. This choice is non-trivial, as performance varies widely across datasets, heterogeneity levels, and compute constraints. We present an end-to-end framework that automates, streamlines, and adapts aggregation strategy selection for federated learning. The framework operates in two modes: a single-trial mode, where large language models infer suitable strategies from user-provided or automatically detected data characteristics, and a multi-trial mode, where a lightweight genetic search efficiently explores alternatives under constrained budgets. Extensive experiments across diverse datasets show that our approach enhances robustness and generalisation under non-IID conditions while reducing the need for manual intervention. Overall, this work advances towards accessible and adaptive federated learning by automating one of its most critical design decisions, the choice of an aggregation strategy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。