Federated learning (FL) has received significant attention as a practical alternative to traditional cloud-centric machine learning (ML). The performance (e.g., accuracy and convergence time) of FL is hampered by the selection of clients having non-independent and identically distributed (non-IID) data. In addition, a long convergence time is inevitable if clients with poor computation or communication capabilities participate in the FL procedure (i.e., the straggler problem). To minimize convergence time while guaranteeing high learning accuracy, we first formulate an optimization problem on client selection. As a practical solution, we devise a data distribution-aware online client selection (DOCS) algorithm. In DOCS, the FL server finds several clusters having near IID data and then uses a multi-armed bandit (MAB) technique to select the cluster with the lowest convergence time. The evaluation results demonstrate that DOCS can reduce the convergence time by up to 10% ∼ 41% and improve the learning accuracy by up to 4% ∼ 13% compared to the traditional client selection schemes.
Bibliographical noteFunding Information:
This work was supported in part by the National Research Foundation of Korea funded by the Korean Government (MSIT) under Grants 2020R1A2C3006786 and 2021R1A4A3022102 and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) funded by theKorea government (MSIT) underGrant 2020-0-00974.
© 1967-2012 IEEE.
- Client selection
- federated learning
- multi-armed bandit problem
ASJC Scopus subject areas
- Automotive Engineering
- Aerospace Engineering
- Electrical and Electronic Engineering
- Applied Mathematics