FedCPF: An Efficient-Communication Federated Learning Approach for Vehicular Edge Computing in 6G Communication Networks
FedCPF: эффективный с точки зрения коммуникационных затрат подход к федеративному обучению для периферийных вычислений в транспортных сетях связи 6G
2021-08-03
SCID: 54.1/7bykrmpp
Discuss with AI
6G communication networksFederated learningFlexible aggregationPartial client participationVehicular edge computing
Figures from the paper
Abstract (AI)
The sixth-generation network (6G) is expected to achieve a fully connected world, which makes full use of a large amount of sensitive data. Federated Learning (FL) is an emerging distributed computing paradigm. In Vehicular Edge Computing (VEC), FL is used to protect consumer data privacy. However, using FL in VEC will lead to expensive communication overheads, thereby occupying regular communication resources. In the traditional FL, the massive communication rounds before convergence lead to enormous communication costs. Furthermore, in each communication round, many clients upload large quantity model parameters to the parameter server in the uplink communication phase, which increases communication overheads. Moreover, a few straggler links and clients may prolong training time in each round, which will decrease the efficiency of FL and potentially increase the communication costs. In this work, we propose an efficient-communication approach, which consists of three parts, including “Customized”, “Partial”, and “Flexible”, known as FedCPF. FedCPF provides a customized local training strategy for vehicular clients to achieve convergence quickly through a constraint item within fewer communication rounds. Moreover, considering the uplink congestion, we introduce a partial client participation rule to avoid numerous vehicles uploading their updates simultaneously. Besides, regarding the diverse finishing time points of federated training, we present a flexible aggregation policy for valid updates by constraining the upload time. Experimental results show that FedCPF outperforms the traditional FedAVG algorithm in terms of testing accuracy and communication optimization in various FL settings. Compared with the baseline, FedCPF achieves efficient communication with faster convergence speed and improves test accuracy by 6.31% on average. In addition, the average communication optimization rate is improved by 2.15 times.
Key Findings
1
A constraint-based customized local-training strategy accelerates convergence with fewer communication rounds for vehicular clients.
2
Compared with FedAvg, FedCPF improves test accuracy by 6.31% on average and achieves a 2.15-times average communication optimization rate, with faster convergence across various settings.
3
FedCPF combines customized local training, partial client participation, and flexible aggregation to reduce federated-learning communication overhead in vehicular edge computing.
4
Flexible aggregation accepts valid updates within constrained upload times, reducing the impact of straggler links and clients.
5
Partial client participation mitigates uplink congestion by preventing many vehicles from uploading model updates simultaneously.
Research Object
Federated learning in vehicular edge computing within 6G communication networks
Research Subject
Communication overhead reduction and training-efficiency improvement through convergence speed, partial client participation, and flexible aggregation
Publication Details
Publication Date
2021-08-03
Journal
Publisher
ISSN
Cited by
235
Access Type
Author Information
Download PDF
Subscribe to digest