Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocation

TL;DR

This paper introduces a multi-carrier NOMA-enabled wireless federated learning system that optimizes power and bandwidth allocation to significantly improve convergence speed and reduce communication delays.

Contribution

It proposes a novel MC-NOMA WFL framework with flexible aggregation, introduces WGPTM as a convergence metric, and develops an efficient optimization method for resource allocation.

Findings

Achieves over 40% faster convergence compared to existing methods.

Effectively reduces communication delay in wireless federated learning.

Enhances local model training times by leveraging NOMA technology.

Abstract

Wireless federated learning (WFL) undergoes a communication bottleneck in uplink, limiting the number of users that can upload their local models in each global aggregation round. This paper presents a new multi-carrier non-orthogonal multiple-access (MC-NOMA)-empowered WFL system under an adaptive learning setting of Flexible Aggregation. Since a WFL round accommodates both local model training and uploading for each user, the use of Flexible Aggregation allows the users to train different numbers of iterations per round, adapting to their channel conditions and computing resources. The key idea is to use MC-NOMA to concurrently upload the local models of the users, thereby extending the local model training times of the users and increasing participating users. A new metric, namely, Weighted Global Proportion of Trained Mini-batches (WGPTM), is analytically established to measure the convergence of the new system. Another important aspect is that we maximize the WGPTM to harness the convergence of the new system by jointly optimizing the transmit powers and subchannel bandwidths. This nonconvex problem is converted equivalently to a tractable convex problem and solved efficiently using variable substitution and Cauchy's inequality. As corroborated experimentally using a convolutional neural network and an 18-layer residential network, the proposed MC-NOMA WFL can efficiently reduce communication delay, increase local model training times, and accelerate the convergence by over 40%, compared to its existing alternative.