mlsanityData to 7 Oct 2026

Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning

arXiv 2203.13616 ↗First posted 25 Mar 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-head attention, GCNs become highly accurate but oversized, and their deployment on cheap devices requires their pruning. However, pruning at high regimes usually leads to topologically inconsistent networks with weak generalization. In this paper, we devise a novel method for lightweight GCN design. Our proposed approach parses and selects subnetworks with the highest magnitudes while guaranteeing their topological consistency. The latter is obtained by selecting only accessible and co-accessible connections which actually contribute in the evaluation of the selected subnetworks. Experiments conducted on the challenging FPHA dataset show the substantial gain of our topologically consistent pruning method especially at very high pruning regimes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 111 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

51 of 111 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2017Inductive Representation Learning on Large Graphscited by 6,284
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2014Going Deeper with Convolutionscited by 4,231
38 more
  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  3. 2015Fast R-CNNcited by 2,930
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  9. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  11. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  12. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  13. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  14. 2017Deep Mutual Learningcited by 621
  15. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  16. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  17. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  18. 2018Deep Learning on Graphs: A Surveycited by 393
  19. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  20. 2019Variational Information Distillation for Knowledge Transfercited by 321
  21. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  22. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
  23. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  24. 2019What graph neural networks cannot learn: depth vs widthcited by 195
  25. 2014Recurrent Neural Network Regularizationcited by 189
  26. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  27. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  28. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  29. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 121
  30. 2018Learning graphs from data: A signal representation perspectivecited by 119
  31. 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
  32. 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
  33. 2016Building Deep Networks on Grassmann Manifoldscited by 58
  34. 2018Learning to Solve NP-Complete Problems - A Graph Neural Network for Decision TSPcited by 58
  35. 2019A Unified Framework for Structured Graph Learning via Spectral Constraintscited by 53
  36. 2017Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Videocited by 30
  37. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  38. 2016Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detectioncited by 18

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.