Ada-FFL:Adaptive computing fairness federated learning  

作　　者：Yue Cong Jing Qiu Kun Zhang Zhongyang Fang Chengliang Gao Shen Su Zhihong Tian 

机构地区：[1]The Cyberspace Institute of Advanced Technology,Guangzhou University,Guangzhou,China [2]Pengcheng Lab,Shenzhen,China [3]Carnegie Mellon University,Pittsburgh,Pennsylvania,USA [4]Mohamed Bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates

出　　处：《CAAI Transactions on Intelligence Technology》2024年第3期573-584,共12页智能技术学报（英文）

基　　金：National Natural Science Foundation of China,Grant/Award Number:62272114;Joint Research Fund of Guangzhou and University,Grant/Award Number:202201020380;Guangdong Higher Education Innovation Group,Grant/Award Number:2020KCXTD007;Pearl River Scholars Funding Program of Guangdong Universities(2019);National Key R&D Program of China,Grant/Award Number:2022ZD0119602;Major Key Project of PCL,Grant/Award Number:PCL2022A03。

摘　　要：As the scale of federated learning expands,solving the Non-IID data problem of federated learning has become a key challenge of interest.Most existing solutions generally aim to solve the overall performance improvement of all clients;however,the overall performance improvement often sacrifices the performance of certain clients,such as clients with less data.Ignoring fairness may greatly reduce the willingness of some clients to participate in federated learning.In order to solve the above problem,the authors propose Ada-FFL,an adaptive fairness federated aggregation learning algorithm,which can dynamically adjust the fairness coefficient according to the update of the local models,ensuring the convergence performance of the global model and the fairness between federated learning clients.By integrating coarse-grained and fine-grained equity solutions,the authors evaluate the deviation of local models by considering both global equity and individual equity,then the weight ratio will be dynamically allocated for each client based on the evaluated deviation value,which can ensure that the update differences of local models are fully considered in each round of training.Finally,by combining a regularisation term to limit the local model update to be closer to the global model,the sensitivity of the model to input perturbations can be reduced,and the generalisation ability of the global model can be improved.Through numerous experiments on several federal data sets,the authors show that our method has more advantages in convergence effect and fairness than the existing baselines.

关 键 词：adaptive fariness aggregation FAIRNESS federated learning non-IID 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]