Ensemble Federated Learning With Non-IID Data in Wireless Networks

Zhongyuan Zhao, Jingyi Wang, Wei Hong, Tony Q.S. Quek, Zhiguo Ding, Mugen Peng

研究成果: Article同行評審


Federated learning is a promising technique to implement network intelligence for the sixth generation (6G) communication systems. However, the collected data in wireless networks is non-independent and identically distributed (non-IID), which leads to severe deterioration of model performance. Although various enhanced schemes are proposed, it is still challenging to balance the communication cost and the model performance, due to the scarcity of radio resource for model update in wireless networks. In this paper, an ensemble federated learning paradigm is proposed for handling non-IID data, which is also optimized for its deployment in wireless networks in a cost efficient way. First, the framework of ensemble federated learning is designed. By formulating individual user clusters, intra-cluster federated learning models can be generated to reduce the impact of non-IID data, which can be integrated to adapt to various learning data via model ensemble. Second, the optimization of user cluster formation is studied to improve the performance of ensemble federated learning, which is modeled as a coalition formation game to design a Nash-stable algorithm. Finally, the simulation results on the public data sets are provided to verify the performance gains of our proposed schemes for deploying federated learning with non-IID data in wireless networks.

頁(從 - 到)3557-3571
期刊IEEE Transactions on Wireless Communications
出版狀態Published - 2024 4月 1

All Science Journal Classification (ASJC) codes

  • 電腦科學應用
  • 電氣與電子工程
  • 應用數學


深入研究「Ensemble Federated Learning With Non-IID Data in Wireless Networks」主題。共同形成了獨特的指紋。