CE-Fed: Communication efficient multi-party computation enabled federated learning

• Main Authors: Goh, R.S.M (Author), Kanagavelu, R. (Author), Li, Z. (Author), Samsudin, J. (Author), Wang, S. (Author), Wei, Q. (Author), Yang, Y. (Author), Zhang, H. (Author)
• Format: Article
• Language: English
• Published: Elsevier B.V. 2022
• Subjects: Aggregates; Committee selection; Communication cost; Computational efficiency; Confidential data; Edge computing; Federated learning; Learning systems; Multiparty computation; Multi-party computation; Privacy preserving; Privacy-preserving techniques; Scalability; Secure multi-party computation; Shared model; Train model
• Online Access: View Fulltext in Publisher

 Federated learning (FL) allows a number of parties collectively train models without revealing private datasets. There is a possibility of extracting personal or confidential data from the shared models even-though sharing of raw data is prevented by federated learning. Secure Multi Party Computation (MPC) is leveraged to aggregate the locally-trained models in a privacy preserving manner. However, it results in high communication cost and poor scalability in a decentralized environment. We design a novel communication-efficient MPC enabled federated learning called CE-Fed. In particular, the proposed CE-Fed is a hierarchical mechanism which forms model aggregation committee with a small number of members and aggregates the global model only among committee members, instead of all participants. We develop a prototype and demonstrate the effectiveness of our mechanism with different datasets. Our proposed CE-Fed achieves high accuracy, communication efficiency and scalability without compromising privacy. © 2022 The Author(s)