Joint User Selection and Resource Allocation for Fast Federated Edge Learning

Joint User Selection and Resource Allocation for Fast Federated Edge Learning Identity System

JIANG Zhihui, HE Yinghui, YU Guanding

(College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China )

Abstract: By periodically aggregating local learning updates from edge users, federated edge learning (FEEL) is envisioned as a promising means to reap the benefit of local rich data and protect users’ privacy. However, the scarce wireless communication resource greatly limits the number of participated users and is regarded as the main bottleneck which hinders the development of FEEL. To tackle this issue, we propose a user selection policy based on data importance for FEEL system in this paper. In order to quantify the data importance of each user, we first analyze the relationship between the loss decay and the squared norm of gradient. Then, we formulate a combinatorial optimization problem to maximize the learning efficiency by jointly considering user selection and communication resource allocation. By problem transformation and relaxation, the optimal user selection policy and resource allocation are derived, and a polynomial-time optimal algorithm is developed. Finally, we deploy two common-used deep neural network (DNN) models for simulation. The results validate that our proposed algorithm has strong generalization ability and can attain higher learning efficiency as compared with other traditional algorithms.
Keywords: data importance; federated edge learning; learning accuracy; learning efficiency; resource allocation; user selection