4.7 Article

One Bit Aggregation for Federated Edge Learning With Reconfigurable Intelligent Surface: Analysis and Optimization

Journal

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
Volume 22, Issue 2, Pages 872-888

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TWC.2022.3198881

Keywords

Wireless communication; Training; Resource management; Convergence; Optimization; Bit error rate; Performance evaluation; Federated edge learning; SignSGD; reconfigurable intelligent surface; bit error rate; orthogonal frequency division multiple access

Ask authors/readers for more resources

Federated edge learning (FEEL) is a popular framework that collaboratively trains a global learning model across multiple distributed edge devices, overcoming the limitation of centralized machine learning. To address the issue of communication cost in FEEL, the SignSGD scheme has been proposed, using one-bit gradient quantization with majority vote. However, the performance of one-bit aggregation is affected by wireless propagation error. In this work, we propose a reconfigurable intelligent surface (RIS)-aided communication optimization scheme to alleviate the negative influence of communication error on SignSGD-based FEEL.
As one of the most popular and attractive frameworks for model training, federated edge learning (FEEL) presents a new paradigm, which avoids direct data transmission by collaboratively training a global learning model across multiple distributed edge devices, thus overcoming the disadvantage of centralized machine learning in resource limitations, delay constraints, and privacy issues. However, due to the heavy cost of communicating gradient among edge devices, sharing the parameters of a large-scale neural network can still be time-intensive. To alleviate this bottleneck, an efficient scheme, called SignSGD has been recently proposed, where the one-bit gradient quantization with majority vote is featured at edge devices. Nevertheless, the performance of one-bit aggregation will inevitably deteriorate due to the undesirable propagation error introduced by wireless channels. To address this issue, we propose in this work a novel reconfigurable intelligent surface (RIS)-aided one-bit communication optimization scheme under orthogonal frequency division multiple access (OFDMA) to relieve the negative influence of communication error on the SignSGD-based FEEL. Specifically, a learning convergence analysis is firstly presented to quantitatively characterize the impact of wireless communication error measured by the union bound on pairwise bit error rate (BER) on the performance of SignSGD-based FEEL. Immediately, a unified communication-learning optimization problem is further formulated to jointly optimize the sub-band assignment strategy, the power allocation vector, and the RIS configuration matrix. Numerical experiments show that the proposed design achieves substantial performance improvement compared with the state-of-the-art approaches.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available