Over-the-Air Federated Multi-Task Learning via Model Sparsification and Turbo Compressed Sensing

no code implementations • 8 May 2022 • Haoming Ma, Xiaojun Yuan, Zhi Ding, Dian Fan, Jun Fang

To achieve communication-efficient federated multitask learning (FMTL), we propose an over-the-air FMTL (OAFMTL) framework, where multiple learning tasks deployed on edge devices share a non-orthogonal fading channel under the coordination of an edge server (ES).

Multi-Task Learning

Over-the-Air Federated Multi-Task Learning

no code implementations • 27 Jun 2021 • Haoming Ma, Xiaojun Yuan, Dian Fan, Zhi Ding, Xin Wang, Jun Fang

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).

Federated Learning Multi-Task Learning

Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learning

no code implementations • 3 Mar 2021 • Dian Fan, Xiaojun Yuan, Ying-Jun Angela Zhang

In this paper, we investigate over-the-air model aggregation in a federated edge learning (FEEL) system.