一种基于改进NSGA-Ⅲ的联邦学习进化多目标优化算法  

Federated Learning Evolutionary Multi-objective Optimization Algorithm Based on Improved NSGA-Ⅲ

作　　者：胡康琦 马武彬[1] 戴超凡[1] 吴亚辉[1] 周浩浩 HU Kangqi;MA Wubin;DAI Chaofan;WU Yahui;ZHOU Haohao(National Key Laboratory of Information Systems Engineering,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学信息系统工程全国重点实验室,长沙410073

出　　处：《计算机科学》2025年第3期152-160,共9页Computer Science

基　　金：国家自然科学基金面上项目(61871388)。

摘　　要：联邦学习是一种新型的分布式机器学习方法,可以在不共享原始数据的前提下训练模型。当前,联邦学习方法存在针对模型准确率最优化、通信成本最优化、参与者性能分布均衡等多个目标同时优化难的问题,难以做到多目标的同步均衡。针对该问题,提出联邦学习四目标优化模型及求解算法。将全局模型错误率、模型准确率分布方差、通信成本、数据成本作为优化目标,构建优化模型。同时,针对该模型的求解搜索空间大,传统NSGA-Ⅲ算法难以寻优的问题,提出基于佳点集初始化策略的改进NSGA-Ⅲ联邦学习多目标优化算法GPNSGA-Ⅲ(Good Point Set Initialization NSGA-Ⅲ),以求取Pareto最优解。该算法通过佳点集初始化策略将有限的初始化种群以均匀的方式分布在目标求解空间中,相较于原始算法,使第一代解最大限度地接近最优值,提升寻优能力。实验结果证明,GPNSGA-Ⅲ算法得到的Pareto解的超体积值相较于NSGA-Ⅲ算法平均提升107%;Spacing值相较于NSGA-Ⅲ算法平均下降32.3%;对比其他多目标优化算法,GPNSGA-Ⅲ算法能在保证模型准确率的情况下,更有效地实现模型分布方差、通信成本和数据成本的均衡。Federated learning is a novel distributed machine learning method that can train models without sharing raw data.Current federated learning methods suffer from the problem that it is difficult to optimize multiple objectives simultaneously,such as optimizing the model accuracy,optimizing communication costs and balancing the distribution of participants’performance.A four-objective optimization model and a solution algorithm for federated learning are proposed to address this problem.Data usage cost,global model error rate,model accuracy distribution variance and communication cost are taken as the optimization objectives to construct the optimization model.Aiming at the problem that the solution space of this model is large and the traditional NSGA-Ⅲ algorithm is difficult to find the optimal solution,the improved NSGA-Ⅲ federated learning multi-objective optimization algorithm GPNSGA-Ⅲ based on the Good Point Set initialization strategy is proposed to find the Pareto optimal solution.The algorithm uniformly distributes the limited initialization populations in the objective solution space through the good point set initialization strategy,so that the first-generation solution is maximally close to the optimal value and the ability to find the optimal value is improved compared with the original algorithm.Experimental results show that the hypervolume value of the Pareto solution obtained by the GPNSGA-Ⅲ algorithm is improved by 107% on average compared with the NSGA-Ⅲ algorithm;the Spacing value is reduced by 32.3% on average compared with the NSGA-Ⅲ algorithm;compared with the other multi-objective optimization algorithms,the GPNSGA-Ⅲ algorithm is more effective in achieving the accuracy of the model while guaranteeing the ba-lance of model accuracy distribution variance,communication cost and data cost.

关 键 词：联邦学习 多目标寻优 佳点集 NSGA-Ⅲ算法 参数优化 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]