少模型服务多客户端的个性化联邦学习
Few-for-Many Personalized Federated Learning
把个性化联邦学习重新表述为「少模型服务多客户端」的多目标优化问题，用 K 个共享服务器模型覆盖 M 个异构客户端，可直接迁移到视觉场景下多域/多设备数据异构的协同训练，例如多摄像头或多医院影像数据下的模型个性化。
原文依据 we reformulate PFL as a few-for-many optimization problem that maintains only K shared server models (K << M) to collectively serve all M clients
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论个性化联邦学习（PFL）旨在为数据分布高度异构的客户端训练定制模型，同时保护数据隐私。现有方法往往依赖聚类或模型插值等启发式手段，缺乏在异构客户端目标之间取得平衡的原则性机制。为数据分布各异的 M 个客户端提供服务本质上是一个多目标优化问题，要实现最优个性化，理想情况下需要在帕累托前沿上得到 M 个不同的模型。然而，在拥有数百或数千个客户端的联邦场景中，维护 M 个独立模型会带来显著的扩展性挑战。为应对这一挑战，我们将 PFL 重新表述为一个「少模型服务多客户端」的优化问题，仅维护 K 个共享服务器模型（K << M）来共同服务全部 M 个客户端。我们证明该框架能够实现接近最优的个性化：近似误差随 K 增大而减小，且随着数据量增长，每个客户端的模型会收敛到该客户端的最优点。基于这一重新表述，我们提出 FedFew，一种通过高效的基于梯度的更新来联合优化 K 个服务器模型的实用算法。与需要人工划分客户端的聚类方法或需要仔细调参的插值方法不同，FedFew 通过其优化过程自动发现最优的模型多样性。在视觉、自然语言处理以及真实医学影像数据集上的实验表明，FedFew 仅用 3 个模型即可持续优于其他最优方法。代码见 https://github.com/pgg3/FedFew。
英文原文摘要 1660 字符
Personalized Federated Learning (PFL) aims to train customized models for clients with highly heterogeneous data distributions while preserving data privacy. Existing approaches often rely on heuristics like clustering or model interpolation, which lack principled mechanisms for balancing heterogeneous client objectives. Serving M clients with distinct data distributions is inherently a multi-objective optimization problem, where achieving optimal personalization ideally requires M distinct models on the Pareto front. However, maintaining M separate models poses significant scalability challenges in federated settings with hundreds or thousands of clients. To address this challenge, we reformulate PFL as a few-for-many optimization problem that maintains only K shared server models (K << M) to collectively serve all M clients. We prove that this framework achieves near-optimal personalization: the approximation error diminishes as K increases and each client's model converges to each client's optimum as data grows. Building on this reformulation, we propose FedFew, a practical algorithm that jointly optimizes the K server models through efficient gradient-based updates. Unlike clustering-based approaches that require manual client partitioning or interpolation-based methods that demand careful hyperparameter tuning, FedFew automatically discovers the optimal model diversity through its optimization process. Experiments across vision, NLP, and real-world medical imaging datasets demonstrate that FedFew, with just 3 models, consistently outperforms other state-of-the-art approaches. Code is available at https://github.com/pgg3/FedFew.