Federated Learning Aggregation Algorithm Based on AP Clustering Algorithm
In traditional federation learning,multiple clients'local models are trained independently from their private data,and the central server generates a shared global model by aggregating the local models.However,due to statistical heterogeneity such as non-independent identically distributed(Non-IID)data,a global model often cannot be adapted to each client.To ad-dress this problem,this paper proposes an AP clustering algorithm-based federation learning aggregation algorithm(APFL)for Non-IID data.In APFL,the server calculates the similarity matrix between each client based on the data characteristics of the clients,and then uses the AP clustering algorithm to divide the clients into different clusters and construct a polycentric frame-work to calculate the suitable personalized model weights for each client.This algorithm is experimented on FMINST dataset and CIFAR10 dataset,and APFL improves 1.88 percentage points on FMNIST dataset and 6.08 percentage points on CIFAR10 data-set compared with traditional Federated Learning FedAvg.The results show that the proposed APFL improves the accuracy perfor-mance of Federated Learning on Non-IID data in this paper.
federal learningnon-independent identical distributionAP clustering algorithm
国家科技期刊平台
NSTL
万方数据
