mlsanityData to 7 Oct 2026

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

arXiv 1903.10258 ↗First posted 25 Mar 2019cs.CVcited by 226

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single PruningNet trained for the target network, we can search for various Pruned Networks under different constraints with little human participation. Compared to the state-of-the-art pruning methods, we have demonstrated superior performances on MobileNet V1/V2 and ResNet. Codes are available on https://github.com/liuzechun/MetaPruning.

Key facts. Cited by 226 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 68; 2022: 52; 2023: 45; 2024: 28; 2025: 24; 2026: 9.

226 papers.

Sort:

By area:

  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2023DepGraph: Towards Any Structural Pruningcited by 202
  3. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  4. 2022Structured Pruning Learns Compact and Accurate Modelscited by 167
  5. 2022On-Device Training Under 256KB Memorycited by 158
  6. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  7. 2021Group Fisher Pruning for Practical Network Compressioncited by 130
  8. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  9. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  10. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 87
  11. 2021Dynamic Slimmable Networkcited by 83
  12. 2021Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimationcited by 78
38 more
  1. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  2. 2023Oscillation-free Quantization for Low-bit Vision Transformerscited by 55
  3. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  4. 2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
  5. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  6. 2022Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Modelscited by 44
  7. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 43
  8. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  9. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  10. 2022Structural Pruning via Latency-Saliency Knapsackcited by 40
  11. 2024Tiny Machine Learning: Progress and Futurescited by 40
  12. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  13. 2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
  14. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
  15. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  16. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  17. 2021Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decompositioncited by 33
  18. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  19. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  20. 2022Learning Best Combination for Efficient N:M Sparsitycited by 32
  21. 2022Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterizationcited by 31
  22. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  23. 2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
  24. 2021GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarizationcited by 29
  25. 2021Locally Free Weight Sharing for Network Width Searchcited by 27
  26. 2021Effective Model Sparsification by Scheduled Grow-and-Prune Methodscited by 25
  27. 2021BCNet: Searching for Network Width with Bilaterally Coupled Networkcited by 23
  28. 2021Carrying out CNN Channel Pruning in a White Boxcited by 22
  29. 2026SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Passcited by 22
  30. 2024Isomorphic Pruning for Vision Modelscited by 21
  31. 2022Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolutioncited by 20
  32. 2022Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptionscited by 20
  33. 2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratchcited by 20
  34. 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
  35. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  36. 2022DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networkscited by 19
  37. 2023Principled Weight Initialization for Hypernetworkscited by 19
  38. 2021HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworkscited by 18

50 most cited of 226 All 226 (JSON)