Work

Federated Learning with Random Communication and Dynamic Aggregation

Year: 2021

Type: conference-paper

Abstract: Federated Learning (FL) is a setting that allows clients to train a joint global model collaboratively while keeping data locally. Due to FL has advantages of data confidential and distributed computing, interest in this area has increased. In this paper, we designed a new FL algorithm named FedRAD. Random communication and dynamic aggregation methods are proposed for FedRAD. Random communication method enables FL system use the combination of fixed communication interval and constrained variable intervals in a single task. Dynamic aggregation method reforms aggregation weights and makes weights update automately. Both methods aim to improve model performance. We evaluated two proposed methods respectively, and compared FedRAD with three algorithms on three hyperparameters. Results at CIFAR-10 demonstrate that each method has good performance, and FedRAD can achieve higher classification accuracy than state-of-the-art FL algorithms.

Source: International Conference on Machine Learning Techniques and Data Science (MLDS)

DOI: 10.5121/csit.2021.111816

Authors: Ruolin Huang, Ting Lu, Yiyang Luo, Guohua Liu, Shan Chang

Institution: Donghua University

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: Natural Science Foundation of Shanghai

Awards: 多能量源无线充电传感器网络关键技术研究, G8802333620