DNNShifter : An efficient DNN pruning system for edge computing

Bailey J Eccles*, Philip Rodgers, Peter Kilpatrick, Ivor Spence, Blesson Varghese

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
20 Downloads (Pure)


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.
Original languageEnglish
Number of pages14
JournalFuture Generation Computer Systems
Early online date23 Sept 2023
Publication statusEarly online date - 23 Sept 2023


  • Deep neural networks
  • Machine learning
  • Internet of things
  • Edge computing
  • Model compression
  • Model pruning

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'DNNShifter : An efficient DNN pruning system for edge computing'. Together they form a unique fingerprint.

Cite this