Communication-Efficient and Cross-chain Empowered Federated Learning for Artificial Intelligence of Things

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

47 Scopus Citations
View graph of relations

Author(s)

  • Jiawen Kang
  • Xuandi Li
  • Jiangtian Nie
  • Minrui Xu
  • Zehui Xiong
  • Dusit Niyato
  • Qiang Yan

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)2966-2977
Journal / PublicationIEEE Transactions on Network Science and Engineering
Volume9
Issue number5
Online published30 May 2022
Publication statusPublished - Sept 2022

Abstract

Conventional machine learning approaches aggregate all training data in a central server, which causes massive communication overhead of data transmission and is also vulnerable to privacy leakage. Thereby, blockchain-based federated learning has emerged to protect Artificial Intelligence of Things (AIoT) devices from exposing their private data by the Federated Learning (FL) framework, and also enables decentralized model training without vulnerability of a central server. However, the existing blockchain-based FL systems still suffer from (i) limited scalability of the single blockchain framework; and (ii) large communication costs incurred by iterative large-size model update transmission. To this end, we first design an efficient cross-chain framework for scalable and flexible model training management, in which multiple blockchains are customized for specific FL tasks and individually perform learning tasks for privacy protection. A cross-chain scheme is proposed to enable secure blockchain collaboration and interactions for efficient model training, model trading, and payment. We then propose an efficient gradient compression scheme to save communication cost without compromising accuracy. Moreover, for model trading markets, we design a dynamic pricing scheme using machine learning-based auction for model trading. Numerical results demonstrate that the proposed framework and schemes achieve scalable, flexible, and communication-efficient decentralized FL system in AIoT.

Research Area(s)

  • 6G mobile communication, Artificial Intelligence of Things, Blockchains, cross-chain, Data models, Federated learning, gradient compression and quantization, Quantization (signal), Servers, Task analysis, Training

Citation Format(s)

Communication-Efficient and Cross-chain Empowered Federated Learning for Artificial Intelligence of Things. / Kang, Jiawen; Li, Xuandi; Nie, Jiangtian et al.
In: IEEE Transactions on Network Science and Engineering, Vol. 9, No. 5, 09.2022, p. 2966-2977.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review