Neural Network Pruning

Ask about this topic

Overview

Neural network pruning studies how to remove parts of a model that contribute little to its predictions, reducing memory use, computation, energy, or latency. Methods range from magnitude-based removal to scores using gradients, Fisher information, curvature, activations, redundancy, or task-specific behavior; they may prune individual weights or structured units such as channels, attention heads, and layers. Pruning can happen during training or after training in one shot or iteratively, often with fine-tuning, distillation, or compensation to recover lost performance. A central challenge is that the best pruning decisions depend on the model, task, calibration data, and hardware, so lower parameter counts do not always translate into faster inference or preserve reliability and reasoning behavior.

Latest papers

CardsList

292 papers37 papers in the last four weeks, up 3% on the four weeks before. 0.2% of all new papers.

  1. Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks

    Mar 16, 2026Xiaoyu He, Weicai Li, Tiejun Lv +1Federated LearningCommunication-Efficient Distributed Training

    School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China · Center for Target Cognition Information Processing Science and Technology, and the Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, both at Beijing Information Science and Technology University, Beijing, China

  2. Spiking Layer-Adaptive Magnitude-based Pruning

    Mar 16, 2026Junqiao Wang, Zhehang Ye, Yuqi OuyangSpiking Neural NetworksNeural Network Pruning

    Sichuan University-Pittsburgh Institute, Sichuan University, Chengdu, 610207, China · College of Computer Science, Sichuan University, Chengdu, 610065, China

  3. Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining

    Mar 15, 2026Chongxin Li, Hanzhang Wang, Lian DuanVLM SafetyVLM Robustness

    School of Computer Engineering and Science, Shanghai University

  4. CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction

    Mar 13, 2026Gang Hu, Yinglei Teng, Pengfei Wu +1Federated LearningHeterogeneous Federated Learning

  5. GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models

    Mar 12, 2026Xiaoyun Liu, Divya Saxena, Jiannong Cao +3LLM PruningStructured Pruning

    Department of Computing, The Hong Kong Polytechnic University, Hong Kong · School of Artificial Intelligence and Data Science, IIT Jodhpur, Jodhpur 342030, India

  6. Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks

    Mar 12, 2026Tianhao Qian, Zhuoxuan Li, Jinde Cao +2Neural Network PruningStructured Sparsity

    the School of Mathematics, Southeast University, Nanjing 210096, China · the School of Mathematics, Southeast University, Nanjing 210096, China, and also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw 01-447, Poland · the School of Cyber Science & Engineering, Southeast University, Nanjing 210096, China +1

  7. Pruning-induced phases in fully-connected neural networks: the eumentia, the dementia, and the amentia

    Mar 12, 2026Haining Pan, Nakul Aggarwal, J. H. PixleyPhase Transitions in Neural NetworksNeural Network Pruning

    Department of Physics and Astronomy, Center for Materials Theory, Rutgers University, Piscataway, NJ 08854 USA · Center for Computational Quantum Physics, Flatiron Institute, New York, New York 10010, USA

  8. HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers

    Mar 12, 2026Andy Li, Aiden Durrant, Milan Markovic +1Efficient ViTsAttention Head Pruning

    School of Natural and Computing Sciences, University of Aberdeen, UK · School of Computing Sciences, University of East Anglia, UK · Department of Physics and Technology, UiT The Arctic University of Norway, Norway

  9. Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning

    Mar 10, 2026Jialei Tan, Zheng Lin, Xiangming Cai +4Distributed TrainingNeural Network Pruning

    School of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China · Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong · School of Electrical Engineering and Telecommunications, University of New South Wales Sydney, Sydney, NSW 2052, Australia +3

  10. Uncovering a Winning Lottery Ticket with Continuously Relaxed Bernoulli Gates

    Mar 9, 2026Itamar Tsayag, Ofir LindenbaumLottery Ticket HypothesisSparse Neural Networks

    Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel

  11. Adaptive MLP Pruning for Large Vision Transformers

    Mar 9, 2026Chengchao ShenNeural Network CompressionNeural Network Pruning

    Central South University

  12. High-Fidelity Pruning for Large Language Models

    Mar 9, 2026Yijun Zhu, Jianxin Wang, Chengchao ShenLLM PruningNeural Network Pruning

    Central South University

  13. Deterministic Differentiable Structured Pruning for Large Language Models

    Mar 9, 2026Weiyu Huang, Pengle Zhang, Xiaolu Zhang +3LLM PruningStructured Pruning

    Department of Computer Science and Technology, Tsinghua University, Beijing, China · Ant Group, Beijing, China

  14. HiPP-Prune: Hierarchical Preference-Conditioned Structured Pruning for Vision-Language Models

    Mar 6, 2026Lincen Bai, Hedi Tabia, Raul Santos-RodriguezLVLM PruningNeural Network Pruning

    Université Paris-Saclay · University of Bristol

  15. EvoESAP: Non-Uniform Expert Pruning for Sparse MoE

    Mar 6, 2026Zongfang Liu, Shengkun Tang, Boyang Sun +2Mixture-of-Experts PruningLLM Pruning

    Zhejiang University, Hangzhou, Zhejiang, China · Westlake University, Hangzhou, Zhejiang, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

  16. ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning

    Mar 6, 2026Mingluo Su, Huan WangLLM PruningNeural Network Pruning

    Westlake University

  17. Diff-ES: Stage-wise Structural Diffusion Pruning via Evolutionary Search

    Mar 5, 2026Zongfang Liu, Shengkun Tang, Zongliang Wu +2Diffusion Model PruningDiffusion Model Inference Acceleration

    Zhejiang University · Westlake University · Mohamed bin Zayed University of Artificial Intelligence

  18. A Benchmark Study of Neural Network Compression Methods for Hyperspectral Image Classification

    Mar 5, 2026Sai ShiNeural Network CompressionNeural Network Quantization

    Department of Computer and Information Science, Temple University, Philadelphia, USA

  19. CA-AFP: Cluster-Aware Adaptive Federated Pruning

    Mar 2, 2026Om Govind Jha, Harsh Shukla, Haroon R. LoneFederated LearningNeural Network Pruning

    IISER Bhopal Bhopal, India

  20. Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning

    Feb 28, 2026Patrick Stricker, Florian Röhrbein, Andreas KnoblauchEnergy-Efficient MLBiologically Plausible Learning

    KEIM Institute, Albstadt-Sigmaringen University, Germany · Department of Computer Science, Chemnitz University of Technology, Germany

  21. Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction

    Feb 27, 2026Amir AsiaeeStructural Causal ModelsCausal Abstraction

    Vanderbilt University Medical Center Nashville, TN

  22. GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks

    Feb 27, 2026Wenwu Tang, Dong Wang, Lothar Thiele +1Neural Network CompressionNeural Network Pruning

    Graz University of Technology · ETH Zurich, Switzerland · Complexity Science Hub, Austria

  23. Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies

    Feb 26, 2026George BirdDynamic Neural NetworksNeural Network Activation Functions

    Department of Computer Science, University of Manchester, UK

  24. LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation

    Feb 26, 2026Shouwei Gao, Xu Zheng, Dongsheng Luo +2Scientific MLAutomated Machine Learning

    Oregon State University · Florida International University · Argonne National Laboratory

  25. OnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting

    Feb 25, 2026Matteo Risso, Alessio Burrello, Daniele Jahier PagliariNeural Network PruningStructured Pruning

    Politecnico di Torino, Italy

  26. X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation

    Feb 25, 2026Abdul Karim Gizzini, Yahia MedjahdiChannel EstimationEfficient Neural Network Inference

    University of Paris-Est Créteil (UPEC), LISSI/TincNET, F-94400, Vitry-sur-Seine, France. · IMT Nord Europe, Institut Mines Télécom, Centre for Digital Systems, F-59653 Villeneuve d’Ascq, France.

  27. Sparsity Induction for Accurate Post-Training Pruning of Large Language Models

    Feb 25, 2026Minhao Jiang, Zhikai Li, Xuewen Liu +3LLM PruningLLM Compression

    Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

  28. Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators

    Feb 24, 2026Atousa Jafari, Mahdi Taheri, Hassan Ghasemzadeh Mohammadi +2Reservoir ComputingNeural Network Compression

    Paderborn University, Paderborn, Germany · Brandenburg Technical University, Cottbus, Germany · Tallinn University of Technology, Tallinn, Estonia +1

  29. Elimination-compensation pruning for fully-connected neural networks

    Feb 24, 2026Enrico Ballini, Luca Muscarnera, Alessio Fumagalli +2Neural Network PruningNeural Network Compression

    MOX, Department of Mathematics, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano, Italy

  30. Unlearning Noise in PINNs: A Selective Pruning Framework for PDE Inverse Problems

    Feb 23, 2026Yongsheng Chen, Yong Chen, Wei Guo +1Physics-Informed MLPDE Inverse Problems

    School of Mathematical Sciences, Zhejiang University, Hangzhou 310027, China. · Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA 19104, USA. · Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX 70409, USA.