Pruning Analog Over-the-Air Distributed Learning Models with Accuracy Loss Guarantee

Kailei Xu, Howard H. Yang, Zhongyuan Zhao, Wei Hong, Tony Q.S. Quek, Mugen Peng

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Analog over-the-air computing enables a swarm of end-user devices to efficiently conduct distributed learning, where the intermediate parameters of users, such as gradients, are modulated and transmitted via a group of orthogonal waveforms, and can be mixed directly at a server without individually detecting the feedback parameters of each user. Nonetheless, the scarcity of orthogonal waveforms, as well as communication resources of the end-user devices, are throttling this paradigm in adopting complex deep learning models. To balance the tradeoff between communication efficiency and accuracy performance, we study model pruning for analog over-the-air distributed learning in this paper. First, a model pruning scheme is proposed to improve the communication efficiency of analog over-the-air training. An importance measure for model parameter pruning is also designed based on the analog over-the-air aggregated gradient, which can characterize the contribution of each parameter without removing channel fading and electromagnetic interference. Second, an analytical expression of the training error upper bound is derived, which shows the proposed scheme is able to converge even when the aggregated gradient is corrupted by heavy-tailed electromagnetic interference with an infinite variance. Finally, several experimental results are provided to show the performance gains achieved by our proposed scheme, and also verify the correctness of analytical results.

Original languageEnglish
Title of host publicationICC 2022 - IEEE International Conference on Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781538683477
Publication statusPublished - 2022
Event2022 IEEE International Conference on Communications, ICC 2022 - Seoul, Korea, Republic of
Duration: 2022 May 162022 May 20

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607


Conference2022 IEEE International Conference on Communications, ICC 2022
Country/TerritoryKorea, Republic of

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Pruning Analog Over-the-Air Distributed Learning Models with Accuracy Loss Guarantee'. Together they form a unique fingerprint.

Cite this