Communication-efficient federated recommendation model based on many-objective evolutionary algorithm

作者：

Highlights：

• A novel communication-efficient federated recommendation model is proposed.

• A many-objective evolutionary method is used to achieve parameter reduction.

• Recommended performances and communication cost are optimized simultaneously.

摘要

•A novel communication-efficient federated recommendation model is proposed.•A many-objective evolutionary method is used to achieve parameter reduction.•Recommended performances and communication cost are optimized simultaneously.

论文关键词：Federated learning,Recommendation system,Federated recommendation model,Many-objective evolutionary algorithm,RVEA

论文评审过程：Received 5 June 2021, Revised 18 March 2022, Accepted 20 March 2022, Available online 23 March 2022, Version of Record 10 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116963