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

Abstract

Federated learning technology solves the problems of data islands and privacy leakage to a certain extent.However it has shortcomings such as high communication cost,unstable communication,and uneven distribution of participant performance.In order to overcome these shortcomings and achieve a balance between model effectiveness,fairness,and communication costs,an improved NSGA-III algorithm for multi-objective optimization of federated learning is proposed.First,a federated learning multi-objective optimization model is constructed to maximize the accuracy of the global model,minimize the variance of the global mo-del accuracy distribution and minimize the communication cost of participant,and an improved NSGA-III algorithm based on fast greedy initialization is proposed,which improves the efficiency of NSGA-III for multi-objective optimization of federated learning.Experimental results show that the proposed optimization method can obtain a better Pareto solution than the classical multi-objective evolutionary algorithm.Compared with the standard model of federated learning,the optimized model can effectively lower the communication cost and the variance of the global model accuracy distribution while ensuring the accuracy of the global model.