Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges

Shen, Cong; Xu, Jie; Zheng, Sihui; Chen, Xiang

doi:10.1109/mcom.001.2000744

Cited by 32 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation results corroborate the effectiveness of this approach, which demonstrates increased convergence rate without model accuracy degradation. In essence, this observation coincides with the concept of "later-is-better" [23], which implies that reserving FL-related resources in the early stages of the training process and spending them in the final stages, may be beneficial for the performance.…”

Section: B Contributionssupporting

confidence: 67%

Wireless Quantized Federated Learning: A Joint Computation and Communication Design

Bouzinis¹,

Diamantoulakis²,

Karagiannidis³

2022

Preprint

View full text Add to dashboard Cite

Recently, federated learning (FL) has sparked widespread attention as a promising decentralized machine learning approach which provides privacy and low delay. However, communication bottleneck still constitutes an issue, that needs to be resolved for an efficient deployment of FL over wireless networks. In this paper, we aim to minimize the total convergence time of FL, by quantizing the local model parameters prior to uplink transmission. More specifically, the convergence analysis of the FL algorithm with stochastic quantization is firstly presented, which reveals the impact of the quantization error on the convergence rate. Following that, we jointly optimize the computing, communication resources and number of quantization bits, in order to guarantee minimized convergence time across all global rounds, subject to energy and quantization error requirements, which stem from the convergence analysis. The impact of the quantization error on the convergence time is evaluated and the trade-off among model accuracy and timely execution is revealed. Moreover, the proposed method is shown to result in faster convergence in comparison with baseline schemes. Finally, useful insights for the selection of the quantization error tolerance are provided.

show abstract

Section: B Contributionssupporting

confidence: 67%

Wireless Quantized Federated Learning: A Joint Computation and Communication Design

Bouzinis¹,

Diamantoulakis²,

Karagiannidis³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The experimental results show a 40% reduction in the system cost compared to previous state‐of‐the‐art approaches. Furthermore, a novel resource allocation framework termed ‘resource rationing’ was introduced by Shen et al 75 in which it was highlighted that each learning round has a different importance level toward the final performance of the system due to the fact that factors like bandwidth, number of clients and energy limits are unique in each client device. Resource rationing is built upon the “later‐is‐better” principle indicating that there is a significant performance boost if resources are reserved at the early stages of training and then utilized as much as possible in the later rounds.…”

Section: Wireless Communications For Federated Learningmentioning

confidence: 99%

Federated learning and next generation wireless communications: A survey on bidirectional relationship

Shome

Waqar

Khan

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In order to meet the extremely heterogeneous requirements of the next generation wireless communication networks, research community is increasingly dependent on using machine‐learning solutions for real‐time decision‐making and radio resource management. Traditional machine learning employs fully centralized architecture in which the entire training data is collected at one node for example, cloud server, that significantly increases the communication overheads and also raises severe privacy concerns. Toward this end, a distributed machine‐learning paradigm termed as federated learning (FL) has been proposed recently. In FL, each participating edge device trains its local model by using its own training data. Then, via the wireless channels the weights or parameters of the locally trained models are sent to the central parameter server (PS), that aggregates them and updates the global model. On one hand, FL plays an important role for optimizing the resources of wireless communication networks, on the other hand, wireless communications is crucial for FL. Thus, a “bidirectional” relationship exists between FL and wireless communications. Although FL is an emerging concept, many publications have already been published in the domain of FL and its applications for next generation wireless networks. Nevertheless, we noticed that none of the works have highlighted the bidirectional relationship between FL and wireless communications. Therefore, the purpose of this survey article is to bridge this gap in literature by providing a timely and comprehensive discussion on the interdependency between FL and wireless communications.

show abstract

“…Consequently, the issues related to resource heterogeneity have to be considered in future works. As a possible solution, the impact of heterogeneity can be diminished by allocating extra computational resources to participants having bigger amounts of local training data to realize acceptable performance within the permitted time interval and contrariwise [95,96]. In another way, a method to allocate extra communication resources to the participants with weak performance because of shortage in computing resources.…”

Section: • Adaptive Heterogeneous Resource Allocationmentioning

confidence: 99%

Challenges, Opportunities, and Future Prospects

Abdel‐Basset

Moustafa

Hawash

et al. 2021

Deep Learning Techniques for IoT Security and Privacy

View full text Add to dashboard Cite

Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges

Cited by 32 publications

References 9 publications

Wireless Quantized Federated Learning: A Joint Computation and Communication Design

Wireless Quantized Federated Learning: A Joint Computation and Communication Design

Federated learning and next generation wireless communications: A survey on bidirectional relationship

Challenges, Opportunities, and Future Prospects

Contact Info

Product

Resources

About