mlsanityData to 14 Oct 2026

One-Shot Multi-Rate Pruning of Graph Convolutional Networks

arXiv 2312.17615 ↗First posted 29 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights. Our method is variational and proceeds by aligning the weight distribution of the learned networks with an a priori distribution. In the one hand, this allows implementing any fixed pruning rate, and also enhancing the generalization performances of the designed lightweight GCNs. In the other hand, MRMP achieves a joint training of multiple GCNs, on top of shared weights, in order to extrapolate accurate networks at any targeted pruning rate without retraining their weights. Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 62 of its 147 references that are in the map. First posted on arXiv 29 Dec 2023.

Builds on

62 of 147 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2017Mask R-CNNcited by 7,277
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  10. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  11. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  12. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
38 more
  1. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  2. 2019Searching for MobileNetV3cited by 1,994
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  4. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  7. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  8. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  10. 2017Deep Mutual Learningcited by 628
  11. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 583
  12. 2019Improved Knowledge Distillation via Teacher Assistantcited by 573
  13. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  14. 2018Deep Learning on Graphs: A Surveycited by 393
  15. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  16. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  17. 2019Variational Information Distillation for Knowledge Transfercited by 324
  18. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 315
  19. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  20. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  21. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  22. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  23. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  24. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  25. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  26. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  27. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  28. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 122
  29. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  30. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 94
  31. 2017Intel RealSense Stereoscopic Depth Camerascited by 83
  32. 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
  33. 2017Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networkscited by 62
  34. 2016Building Deep Networks on Grassmann Manifoldscited by 58
  35. 2017Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networkscited by 49
  36. 2019A neural network based on SPD manifold learning for skeleton-based hand gesture recognitioncited by 46
  37. 2016Deep Learning on Lie Groups for Skeleton-based Action Recognitioncited by 42
  38. 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37

50 most cited of 62 All 62 (JSON)

Built on by

Not cited yet.