Yuwei Xu, Baokang Zhao*, Huan Zhou, Jinshu Su
CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 609-629, 2024, DOI:10.32604/cmes.2024.053462
Abstract The rapid expansion of artificial intelligence (AI) applications has raised significant concerns about user privacy, prompting the development of privacy-preserving machine learning (ML) paradigms such as federated learning (FL). FL enables the distributed training of ML models, keeping data on local devices and thus addressing the privacy concerns of users. However, challenges arise from the heterogeneous nature of mobile client devices, partial engagement of training, and non-independent identically distributed (non-IID) data distribution, leading to performance degradation and optimization objective bias in FL training. With the development of 5G/6G networks and the integration of cloud computing… More >