mlsanityData to 7 Oct 2026

Methods for Pruning Deep Neural Networks

arXiv 2011.00241 ↗First posted 31 Oct 2020cs.LG cs.NEcited by 49

Not on the map. Why?

Abstract (arXiv)

This paper presents a survey of methods for pruning deep neural networks. It begins by categorising over 150 studies based on the underlying approach used and then focuses on three categories: methods that use magnitude based pruning, methods that utilise clustering to identify redundancy, and methods that use sensitivity analysis to assess the effect of pruning. Some of the key influencing studies within these categories are presented to highlight the underlying approaches and results achieved. Most studies present results which are distributed in the literature as new architectures, algorithms and data sets have developed with time, making comparison across different studied difficult. The paper therefore provides a resource for the community that can be used to quickly compare the results from many different methods on a variety of data sets, and a range of architectures, including AlexNet, ResNet, DenseNet and VGG. The resource is illustrated by comparing the results published for pruning AlexNet and ResNet50 on ImageNet and ResNet56 and VGG16 on the CIFAR10 data to reveal which pruning methods work well in terms of retaining accuracy whilst achieving good compression rates. The paper concludes by identifying some promising directions for future research.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 11; 2024: 14; 2025: 13; 2026: 5.

49 papers.

Sort:

By area:

  1. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  2. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  3. 2024Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensingcited by 46
  4. 2024REEF: Representation Encoding Fingerprints for Large Language Modelscited by 34
  5. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 26
  6. 2024A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trendscited by 16
  7. 2024Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNNcited by 10
  8. 2021Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNNcited by 9
  9. 2023Improving the Transferability of Adversarial Examples via Direction Tuningcited by 9
  10. 2023FPGA Resource-aware Structured Pruning for Real-Time Neural Networkscited by 7
  11. 2022Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementationcited by 6
  12. 2021Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusioncited by 5
37 more
  1. 2021On the Compression of Neural Networks Using ℓ0-Norm Regularization and Weight Pruningcited by 4
  2. 2023Neural Network Pruning by Gradient Descentcited by 4
  3. 2025WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classificationcited by 4
  4. 2023Enhancing Edge Intelligence with Highly Discriminant LNT Featurescited by 3
  5. 2024Bayesian computation with generative diffusion models by Multilevel Monte Carlocited by 3
  6. 2023On The Fairness Impacts of Hardware Selection in Machine Learningcited by 2
  7. 2024Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translationcited by 2
  8. 2024Designing Extremely Memory-Efficient CNNs for On-device Vision Taskscited by 2
  9. 2025MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networkscited by 2
  10. 2025KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devicescited by 2
  11. 2023Adversarial Attacks on Machine Learning in Embedded and IoT Platformscited by 1
  12. 2024Systematic construction of continuous-time neural networks for linear dynamical systemscited by 1
  13. 2024Confident magnitude-based neural network pruningcited by 1
  14. 2025Compressing Multi-Task Model for Autonomous Driving via Pruning and Knowledge Distillationcited by 1
  15. 2025Effective Fine-Tuning with Eigenvector Centrality Based Pruningcited by 1
  16. 2025Self-attention vector output similarities reveal how machines pay attentioncited by 1
  17. 2026Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attackscited by 1
  18. 2026Elimination-compensation pruning for fully-connected neural networkscited by 1
  19. 2022Vision Transformer with Convolutional Encoder-Decoder for Hand Gesture Recognition using 24 GHz Doppler Radarcited by 0
  20. 2023Optimizing Deep Learning Models For Raspberry Picited by 0
  21. 2023Transferability of Winning Lottery Tickets in Neural Network Differential Equation Solverscited by 0
  22. 2023IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Meanscited by 0
  23. 2024Arbitrary-Scale Downscaling of Tidal Current Data Using Implicit Continuous Representationcited by 0
  24. 2024Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Trainingcited by 0
  25. 2024Artificial Neural Networks for Photonic Applications: From Algorithms to Implementationcited by 0
  26. 2024A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNscited by 0
  27. 2024FAST GDRNPP: Improving the Speed of State-of-the-Art 6D Object Pose Estimationcited by 0
  28. 2025Exploring Vision Neural Network Pruning via Screening Methodologycited by 0
  29. 2025Lattice-Based Pruning in Recurrent Neural Networks via Poset Modelingcited by 0
  30. 2025PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMscited by 0
  31. 2025Dimension reduction with structure-aware quantum circuits for hybrid machine learningcited by 0
  32. 2025Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN'scited by 0
  33. 2025Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compressioncited by 0
  34. 2025Neural expressiveness for beyond importance model compressioncited by 0
  35. 2026Responsible AI in Businesscited by 0
  36. 2026Resource-Constrained Affect Modelling via Variance Regularisation Pruningcited by 0
  37. 2026Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Banditscited by 0