Journal article · 2023 · Open access
DNNShifter: An efficient DNN pruning system for edge computing
Future Generation Computer Systems, 152, 43–54 · Published 23 September 2023 · DOI 10.1016/j.future.2023.09.025
In brief
“DNNShifter: An efficient DNN pruning system for edge computing” is a 2023 journal article by Bailey J. Eccles and 4 co-authors, published in Future Generation Computer Systems. OpenAlex counts 39 citations as of 19 November 2026, which puts it in the top 2% of works published in 2023 by citations. It is open access under a CC BY licence: the full text is free to read at Future Generation Computer Systems.
- Citations
- 39
- Most cited in
- 2026 (18)
- Field-weighted impact
- 2.41
- References
- 58
- Authors
- 5
Abstract
Deep neural networks (DNNs) underpin many machine learning applications. Production quality DNN models achieve high inference accuracy by training millions of DNN parameters which has a significant resource footprint. This presents a challenge for resources operating at the extreme edge of the network, such as mobile and embedded devices that have limited computational and memory resources. To address this, models are pruned to create lightweight, more suitable variants for these devices. Existing pruning methods are unable to provide similar quality models compared to their unpruned counterparts without significant time costs and overheads or are limited to offline use cases. Our work rapidly derives suitable model variants while maintaining the accuracy of the original model. The model variants can be swapped quickly when system and network conditions change to match workload demand. This paper presents DNNShifter , an end-to-end DNN training, spatial pruning, and model switching system that addresses the challenges mentioned above. At the heart of DNNShifter is a novel methodology that prunes sparse models using structured pruning - combining the accuracy-preserving benefits of unstructured pruning with runtime performance improvements of structured pruning. The pruned model variants generated by DNNShifter are smaller in size and thus faster than dense and sparse model predecessors, making them suitable for inference at the edge while retaining near similar accuracy as of the original dense model. DNNShifter generates a portfolio of model variants that can be swiftly interchanged depending on operational conditions. DNNShifter produces pruned model variants up to 93x faster than conventional training methods. Compared to sparse models, the pruned model variants are up to 5.14x smaller and have a 1.67x inference latency speedup, with no compromise to sparse model accuracy. In addition, DNNShifter has up to 11.9x lower overhead for switching models and up to 3.8x lower memory utilisation than existing approaches. DNNShifter is available for public use from https://github.com/blessonvar/DNNShifter.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Eccles, B. J., Rodgers, P., Kilpatrick, P., Spence, I. T. A., & Varghese, B. (2023). DNNShifter: An efficient DNN pruning system for edge computing. Future Generation Computer Systems, 152, 43–54. https://doi.org/10.1016/j.future.2023.09.025
MLA 9
Eccles, Bailey J., et al. “DNNShifter: An efficient DNN pruning system for edge computing.” Future Generation Computer Systems, vol. 152, 2023, pp. 43–54. https://doi.org/10.1016/j.future.2023.09.025.
Chicago
Eccles, Bailey J., Philip Rodgers, Peter Kilpatrick, Ivor T. A. Spence, and Blesson Varghese. 2023. “DNNShifter: An efficient DNN pruning system for edge computing.” Future Generation Computer Systems 152: 43–54. https://doi.org/10.1016/j.future.2023.09.025.
Harvard
Eccles, B. J. et al. (2023) ‘DNNShifter: An efficient DNN pruning system for edge computing’, Future Generation Computer Systems, 152, pp. 43–54. doi:10.1016/j.future.2023.09.025.
IEEE
B. J. Eccles, P. Rodgers, P. Kilpatrick, I. T. A. Spence, and B. Varghese, “DNNShifter: An efficient DNN pruning system for edge computing,” Future Generation Computer Systems, vol. 152, pp. 43–54, 2023, doi: 10.1016/j.future.2023.09.025.
BibTeX
@article{eccles2023dnnshifter,
title = {{DNNShifter: An efficient DNN pruning system for edge computing}},
author = {Eccles, Bailey J. and Rodgers, Philip and Kilpatrick, Peter and Spence, Ivor T. A. and Varghese, Blesson},
journal = {Future Generation Computer Systems},
year = {2023},
volume = {152},
pages = {43--54},
doi = {10.1016/j.future.2023.09.025},
url = {https://doi.org/10.1016/j.future.2023.09.025}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 8 | |
| 2025 | 13 | |
| 2026 | 18 |
Its field-weighted citation impact is 2.41: it has been cited 2.41 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- edge computing
- structured pruning
- unstructured pruning
- model switching
- model portfolio
- lightweight inference
- inference latency
- mobile and embedded devices
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Eccles, B. J., Rodgers, P., Kilpatrick, P., Spence, I. T. A., & Varghese, B. (2023). DNNShifter: An efficient DNN pruning system for edge computing. Future Generation Computer Systems, 152, 43–54. https://doi.org/10.1016/j.future.2023.09.025
How many times has this paper been cited?
39 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Future Generation Computer Systems: sign in and open the full text from this page.
Who wrote this paper?
Bailey J. Eccles, Philip Rodgers, Peter Kilpatrick, Ivor T. A. Spence, Blesson Varghese.
What is the DOI of this paper?
10.1016/j.future.2023.09.025, permanently at https://doi.org/10.1016/j.future.2023.09.025. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.