An Energy-Efficient Deep Mutual Learning System Based on D2D-U Communications

Rui Yin, Tingli Wang, Jiantao Yuan, Xianfu Chen, Celimuge Wu, Yusheng Ji

Research output: Contribution to journalArticleScientificpeer-review

Abstract

<italic>Deep mutual learning</italic> (DML) is one of the most high-profile technologies emerging in the field of machine learning during the past few years. DML has the potential of exchanging knowledge on the premise of ensuring data privacy, while retaining the characteristics of local models. In this paper, we design a novel system named as <italic>decentralized mutual learning over unlicensed spectrum</italic> (DML-U), which allows neighbor mobile devices to learn from each other via bidirectional <italic>device-to-device links over unlicensed spectrum</italic> (D2D-U). On this basis, we formulate a non-convex optimization problem for the one-to-one pairing scenario with the goal of minimizing the average communication energy cost for sharing knowledge. We further propose a two-layer iterative algorithm that includes the outer layer based on the enumeration method and the inner layer based on the sum-of-ratios optimization, aiming to find the optimal pairing scheme between devices and obtain the global optimal communication resource allocation scheme, respectively. The numerical results validate the effectiveness of the proposed algorithm in improving the DML performance.

Original languageEnglish
JournalIEEE Transactions on Wireless Communications
DOIs
Publication statusE-pub ahead of print - 2023
MoE publication typeA1 Journal article-refereed

Keywords

  • D2D-U communications
  • Decentralized learning
  • Energy saving
  • Mutual learning
  • Sum-of-ratios

Fingerprint

Dive into the research topics of 'An Energy-Efficient Deep Mutual Learning System Based on D2D-U Communications'. Together they form a unique fingerprint.

Cite this