Quantisation and Pruning for Neural Network Compression and Regularisation
Not on the map. Why?
Abstract (arXiv)
Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jan 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 3; 2023: 2; 2024: 0; 2025: 1.
9 papers.
- 2021Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compressioncited by 38
- 2023Automatic Attention Pruning: Improving and Automating Model Pruning using Attentionscited by 11
- 2021Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activationscited by 6
- 2021Benchmarking Quantized Neural Networks on FPGAs with FINNcited by 2
- 2022DASS: Differentiable Architecture Search for Sparse neural networkscited by 2
- 2022Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networkscited by 2
- 2025Tiny, On-Device Decision Makers with the MiniConv Librarycited by 1
- 2022FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devicescited by 0
- 2023Structured Network Pruning by Measuring Filter-wise Interactionscited by 0
- 2025Tiny, On-Device Decision Makers with the MiniConv Library17 Dec 2025
- 2023Structured Network Pruning by Measuring Filter-wise Interactions3 Jul 2023
- 2023Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions14 Mar 2023
- 2022Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks30 Sep 2022
- 2022DASS: Differentiable Architecture Search for Sparse neural networks14 Jul 2022
- 2022FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices26 May 2022
- 2021Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations15 Oct 2021
- 2021Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression7 Sep 2021
- 2021Benchmarking Quantized Neural Networks on FPGAs with FINN2 Feb 2021