FedRAC：面向联邦学习协作公平的滚动子模型分配
FedRAC: Rolling Submodel Allocation for Collaborative Fairness in Federated Learning
对做视觉模型分布式训练的人，这篇提供了在客户端贡献不均时按信誉滚动分配子模型、并优先训练低频神经元的思路，可直接用于多源视觉数据联合训练时的公平激励与全局模型收敛保障。
原文依据 we propose a rolling submodel allocation module that assigns high-performance submodels to clients with high reputations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习中的协作公平确保客户端按其贡献获得回报，从而促进客户端的长期参与。然而，现有方法在训练早期往往对低贡献客户端回报不足，并忽视了关键问题（局部模型之间的一致性，或全局模型中神经元训练频率不均衡），导致性能下降。为解决这些问题，我们提出 FedRAC，一种采用滚动子模型分配实现协作公平的新型联邦学习框架，且不损害全局模型性能。首先，我们设计了一个具有理论公平性保证的动态信誉计算模块，用于生成与客户端贡献相匹配的信誉。该模块在训练过程中动态调整客户端的信誉，确保低贡献客户端在早期阶段能够获得更好的模型以进行充分训练。其次，我们提出一个滚动子模型分配模块，将高性能子模型分配给高信誉客户端。该模块在分配时优先考虑低频神经元，并具有理论收敛保证，确保全局模型中的所有神经元都得到充分训练。我们在四个公开数据集上进行了大量实验，证实了该方法在公平性和模型准确率方面的优势。源代码见 https://github.com/ZiHuiWangpcl1/FedRAC。
英文原文摘要 1457 字符
Collaborative fairness in federated learning ensures that clients are rewarded according to their contributions, thereby fostering long-term participation among clients. However, existing methods often under-reward low-contributing clients in the early training stage and neglect critical issues (consistency across local models or unequal neuron training frequencies in the global model), leading to degraded performance. To address these issues, we propose FedRAC, a novel Federated learning framework employing Rolling submodel Allocation for Collaborative fairness, without compromising the global model performance. First, we design a dynamic reputation calculation module with a theoretical fairness guarantee to generate reputations matching clients' contributions. It adjusts their reputations dynamically during training, ensuring low-contribution clients access better models in the early stages for adequate training. Second, we propose a rolling submodel allocation module that assigns high-performance submodels to clients with high reputations. This module prioritizes low-frequency neurons during allocation and is supported by theoretical convergence guarantees, ensuring that all neurons in the global model are fully trained. Extensive experiments are conducted on four public datasets to confirm the advantages of our method in terms of fairness and model accuracy. The source code is available at https://github.com/ZiHuiWangpcl1/FedRAC.