Noise-Tolerant Hardware-Aware Pruning for Deep Neural Networks

Shun LU, Cheng CHEN, Kunlong ZHANG, Yang ZHENG, Zheng HU, Wenjing HONG, Guiying LI, Xin YAO

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review


Existing hardware-aware pruning methods for deep neural networks do not take the uncertain execution environment of low-end hardware into consideration. That makes those methods unreliable, since the hardware environments they used for evaluating the pruned models contain uncertainty and thus the performance values contain noise. To deal with this problem, this paper proposes noise-tolerant hardware-aware pruning, i.e., NT-HP. It uses a population-based idea to iteratively generate pruned models. Each pruned model is sent to realistic low-end hardware for performance evaluations. For the noisy values of performance indicators collected from hardware, a threshold for comparison is set, where only the pruned models with significantly better performances are kept in the next generation. Our experimental results show that with the noise-tolerant technique involved, NT-HP can get better pruned models in the uncertain execution environment of low-end hardware. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Original languageEnglish
Title of host publicationAdvances in Swarm Intelligence : 14th International Conference, ICSI 2023, Shenzhen, China, July 14–18, 2023, Proceedings, Part II
EditorsYing TAN, Yuhui SHI, Wenjian LUO
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages12
ISBN (Electronic)9783031366253
ISBN (Print)9783031366246
Publication statusPublished - 2023
Externally publishedYes
Event14th International Conference on Swarm Intelligence - Shenzhen, China
Duration: 14 Jul 202318 Jul 2023

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference14th International Conference on Swarm Intelligence
Abbreviated titleICSI 2023

Bibliographical note

This work was supported the National Natural Science Foundation of China (Grant 62106098, Grant 62272210), the Guangdong Provincial Key Laboratory (Grant 2020B121201001), the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (Grant 2017ZT07X386), the Shenzhen Peacock Plan (Grant KQTD2016112514355531), and the Stable Support Plan Program of Shenzhen Natural Science Fund (Grant 20200925154942002).


  • Deep neural networks
  • Hardware-aware
  • Noise-tolerant neural network pruning
  • Pruning


Dive into the research topics of 'Noise-Tolerant Hardware-Aware Pruning for Deep Neural Networks'. Together they form a unique fingerprint.

Cite this