arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.10751cs.LG
收藏

基于双层优化的自适应加权节点联邦学习

Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization

University of Iowa(爱荷华大学);University of Virginia(弗吉尼亚大学)

Yankun Huang, Qihang Lin, Nick Street, Stephen Baek

摘要:

我们提出了一种带有加权节点的联邦学习方法,其中可以修改权重以优化模型在单独验证集上的性能。该问题被制定为一个双层优化,其中内部问题是一个带有加权节点的联邦学习问题,外部问题的重点是根据内部问题返回的模型的验证性能来优化权重。设计了一种通信效率高的联邦优化算法来解决这个双层优化问题。在误差约束的假设下,我们分析了输出模型的泛化性能,并确定了我们的方法在理论上优于仅在本地训练模型和具有静态和均匀分布权重的联邦学习的情况。

英文摘要:

We propose a federated learning method with weighted nodes in which the weights can be modified to optimize the model's performance on a separate validation set. The problem is formulated as a bilevel optimization where the inner problem is a federated learning problem with weighted nodes and the outer problem focuses on optimizing the weights based on the validation performance of the model returned from the inner problem. A communication-efficient federated optimization algorithm is designed to solve this bilevel optimization problem. Under an error-bound assumption, we analyze the generalization performance of the output model and identify scenarios when our method is in theory superior to training a model only locally and to federated learning with static and evenly distributed weights.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑