Over-the-Air Federated Multi-Task Learning

TL;DR

This paper proposes an over-the-air federated multi-task learning framework that leverages superimposed transmissions over fading channels, significantly enhancing communication efficiency while maintaining learning performance.

Contribution

It introduces a novel OA-FMTL framework integrating over-the-air computation with multi-task learning and develops a Turbo-CS algorithm for effective model aggregation.

Findings

Reduces number of channel uses in federated learning

Maintains learning accuracy with over-the-air transmission

Demonstrates improved system efficiency through convergence analysis

Abstract

In this letter, we introduce over-the-air computation into the communication design of federated multi-task learning (FMTL), and propose an over-the-air federated multi-task learning (OA-FMTL) framework, where multiple learning tasks deployed on edge devices share a non-orthogonal fading channel under the coordination of an edge server (ES). Specifically, the model updates for all the tasks are transmitted and superimposed concurrently over a non-orthogonal uplink fading channel, and the model aggregations of all the tasks are reconstructed at the ES through a modified version of the turbo compressed sensing algorithm (Turbo-CS) that overcomes inter-task interference. Both convergence analysis and numerical results show that the OA-FMTL framework can significantly improve the system efficiency in terms of reducing the number of channel uses without causing substantial learning performance degradation.