mlsanityData to 7 Oct 2026

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

arXiv 2102.03214 ↗First posted 5 Feb 2021cs.CV cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach with state-of-the-art model compression methods. We evaluated our method on various models from typical to mobile-friendly networks, such as ResNet family, VGG-16, MobileNet-v1/v2, and ShuffleNet. Results show that our method can achieve higher compression ratios with a minimal fine-tuning cost yet yields outstanding and competitive performance.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 46 of its 62 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

46 of 62 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2015Continuous control with deep reinforcement learningcited by 3,279
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  12. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
34 more
  1. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  2. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  4. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  5. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  6. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  7. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  8. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  9. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  10. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  11. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  12. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 146
  13. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 121
  14. 2018A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multiplierscited by 118
  15. 2020BRP-NAS: Prediction-based NAS using GCNscited by 109
  16. 2019Provable Filter Pruning for Efficient Neural Networkscited by 98
  17. 2020APQ: Joint Search for Network Architecture, Pruning and Quantization Policycited by 98
  18. 2020SCOP: Scientific Control for Reliable Neural Network Pruningcited by 92
  19. 2020EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruningcited by 80
  20. 2018AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inferencecited by 77
  21. 2019Towards Efficient Model Compression via Learned Global Rankingcited by 75
  22. 2020Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compressioncited by 72
  23. 2020Good Subnetworks Provably Exist: Pruning via Greedy Forward Selectioncited by 70
  24. 2020DMCP: Differentiable Markov Channel Pruning for Neural Networkscited by 68
  25. 2020DHP: Differentiable Meta Pruning via HyperNetworkscited by 57
  26. 2020A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAScited by 53
  27. 2019AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Ratescited by 49
  28. 2020DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocationcited by 47
  29. 2019NAT: Neural Architecture Transformer for Accurate and Compact Architecturescited by 33
  30. 2020Auto Graph Encoder-Decoder for Neural Network Pruningcited by 26
  31. 2020Learnable Motion Coherence for Correspondence Pruningcited by 20
  32. 2020NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Accelerationcited by 16
  33. 2019DiCENet: Dimension-wise Convolutions for Efficient Networkscited by 6
  34. 2017Structured Probabilistic Pruning for Convolutional Neural Network Accelerationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 12; 2024: 9; 2025: 6; 2026: 1.

30 papers.

Sort:

By area:

  1. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  2. 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 49
  3. 2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratchcited by 20
  4. 2021SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learningcited by 11
  5. 2022Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusioncited by 10
  6. 2023Bridging the Gap Between Foundation Models and Heterogeneous Federated Learningcited by 9
  7. 2024Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignmentcited by 9
  8. 2024An Effective Information Theoretic Framework for Channel Pruningcited by 7
  9. 2024Effective Layer Pruning Through Similarity Metric Perspectivecited by 6
  10. 2024SNP: Structured Neuron-level Pruning to Preserve Attention Scorescited by 5
  11. 2023UPSCALE: Unconstrained Channel Pruningcited by 4
  12. 2023Lossy and Lossless (L2) Post-training Model Size Compressioncited by 4
18 more
  1. 2023Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalitiescited by 4
  2. 2023Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approachcited by 2
  3. 2023LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratchcited by 2
  4. 2023A Differentiable Framework for End-to-End Learning of Hybrid Structured Compressioncited by 1
  5. 2024AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstructioncited by 1
  6. 2024Rethinking Pruning for Backdoor Mitigation: An Optimization Perspectivecited by 1
  7. 2024AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learningcited by 1
  8. 2025One-Cycle Structured Pruning via Stability-Driven Subnetwork Searchcited by 1
  9. 2025Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruningcited by 1
  10. 2023Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruningcited by 0
  11. 2023Structured Network Pruning by Measuring Filter-wise Interactionscited by 0
  12. 2023OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detectioncited by 0
  13. 2024Layer Pruning with Consensus: A Triple-Win Solutioncited by 0
  14. 2025Pruning Everything, Everywhere, All at Oncecited by 0
  15. 2025Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learningcited by 0
  16. 2025CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systemscited by 0
  17. 2025Adaptive Graph Pruning with Sudden-Events Evaluation for Traffic Prediction using Online Semi-Decentralized ST-GNNscited by 0
  18. 2026Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networkscited by 0