Time efficient joint optimization federated learning over wireless communication networks

Sun, Junshuai; Wang, Yingying; Sun, Xingming; Li, Na; Nie, Gaofeng

doi:10.23919/jcc.2022.06.013

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10.1109/TWC.2023.3277037 constraint (17). The received signal vector at the BS in the FD communication is expressed as…”

Section: )mentioning

confidence: 99%

“…Amiri et al in [16] optimized the test accuracy to schedule devices and allocate power across time slots. Sun et al improved the training efficiency by jointly considering the effects of uplink resource, energy consumption and latency constraints [17]. Bouzinis et al in [18] considered the problem of minimizing the total delay in each round of FL process in the case of compute-then-transmit non-orthogonal multiple access (NOMA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Massive MIMO for Serving Federated Learning and Non-Federated Learning Users

Farooq

Ngo

et al. 2024

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a promising learning framework for beyond 5G wireless networks. It is anticipated that future wireless networks will jointly serve both FL and downlink non-FL user groups in the same time-frequency resource. While in the downlink of each FL iteration, both groups simultaneously receive data from the base station in the same time-frequency resource, the uplink of each FL iteration requires bidirectional communication to support uplink transmission for FL users and downlink transmission for non-FL users. To overcome this challenge, we present half-duplex (HD) and fullduplex (FD) communication schemes to serve both groups. More specifically, we adopt the massive multiple-input multiple-output technology and aim to maximize the minimum effective rate of non-FL users under a quality of service (QoS) latency constraint for FL users. Since the formulated problem is nonconvex, we propose a power control algorithm based on successive convex approximation to find a stationary solution. Numerical results show that the proposed solutions perform significantly better than the considered baselines schemes. Moreover, the FD-based scheme outperforms the HD-based counterpart in scenarios where the self-interference is small or moderate and/or the size of FL model updates is large.

show abstract

Section: )mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Massive MIMO for Serving Federated Learning and Non-Federated Learning Users

Farooq

Ngo

et al. 2024

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

“…Optimal client associations were also studied to minimize the number of edge-cloud communication rounds [27], loss function [28], Kullback-Leibler divergence (KLD) of data distributions [29], or learning latency [30]. A twolayer algorithm based on genetic algorithm and alternating optimization was proposed to minimize the weighted sum of the optimality gap and overall latency in [31]. A joint helper scheduling and wireless resource allocation scheme was proposed in [32] to capture the importance of weighted gradient.…”

Section: Related Workmentioning

confidence: 99%

“…Several pioneering works have attempted to optimize resource allocation or client scheduling policies for HFL systems [21]- [37]. These studies usually considered a static cloud aggregation process (or global iteration), for which fixed resource allocation and/or client scheduling decisions were made off-line, e.g., using game theory [26], [34], convex approximation [21], [30], [32], and alternating optimization [31]. These studies, in general, cannot adapt to dynamically changing HFL systems with time-varying wireless channels.…”

Section: Introductionmentioning

confidence: 99%

Two-Phase Deep Reinforcement Learning of Dynamic Resource Allocation and Client Selection for Hierarchical Federated Learning

Chen

et al. 2022

2022 IEEE/CIC International Conference on Communications in China (ICCC)

View full text Add to dashboard Cite

Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as "TP-DDPG", to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggleraware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.

show abstract

Time efficient joint optimization federated learning over wireless communication networks

Cited by 2 publications

References 0 publications

Massive MIMO for Serving Federated Learning and Non-Federated Learning Users

Massive MIMO for Serving Federated Learning and Non-Federated Learning Users

Two-Phase Deep Reinforcement Learning of Dynamic Resource Allocation and Client Selection for Hierarchical Federated Learning

Contact Info

Product

Resources

About