상세정보
학술지
Data Distribution-Aware Online Client Selection Algorithm for Federated Learning in Heterogeneous Networks
- 저자
- 이재욱, 고한얼, 서상원, 백상헌
- 발행일
- 202301
- 출처
- IEEE Transactions on Vehicular Technology, v.72 no.1, pp.1127-1136
- ISSN
- 0018-9545
- 출판사
- IEEE
- 협약과제
- 22HH8100, 고신뢰·저지연 5G+ 코어 네트워크 및 5G-TSN 스위치 기술 개발, 김창기
- 초록
- 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.
- KSP 제안 키워드
- Cloud-centric, Data Distribution, Federated learning, Machine learning (ml), Multi-Armed bandits, Optimization problem, Straggler problem, convergence time, heterogeneous network(HetNet), selection algorithm