Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing

• Published in: IEEE transactions on parallel and distributed systems Vol. 33; no. 3; pp. 630 - 641
• Main Authors: Mills, Jed, Hu, Jia, Min, Geyong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; adaptive optimization; Algorithms; Artificial neural networks; Computational modeling; Convergence; Customization; Data models; deep learning; Edge computing; Electronic devices; Federated learning; Iterative methods; Machine learning; Model accuracy; multi-task learning; Neural networks; Optimization; Servers; Training

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the...