mlsanityData to 7 Oct 2026

Training Lightweight Graph Convolutional Networks with Phase-field Models

arXiv 2212.09415 ↗First posted 19 Dec 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs). PFMs exhibit a bi-phase behavior using a particular ultra-local term that allows training both the topology and the weight parameters of GCNs as a part of a single "end-to-end" optimization problem. Our proposed solution also relies on a reparametrization that pushes the mask of the topology towards binary values leading to effective topology selection and high generalization while implementing any targeted pruning rate. Both masks and weights share the same set of latent variables and this further enhances the generalization power of the resulting lightweight GCNs. Extensive experiments conducted on the challenging task of skeleton-based recognition show the outperformance of PFMs against other staple regularizers as well as related lightweight design methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 55 of its 114 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

55 of 114 references.

References · 55

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  7. 2017Graph Attention Networkscited by 8,854
  8. 2017Inductive Representation Learning on Large Graphscited by 6,284
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  11. 2015Fast R-CNNcited by 2,930
  12. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
38 more
  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  4. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  6. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  8. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  9. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  10. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  11. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  12. 2015Gated Graph Sequence Neural Networkscited by 792
  13. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  14. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  15. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  16. 2017Deep Mutual Learningcited by 621
  17. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  18. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  19. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  20. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  21. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  22. 2015Deep Learning with Limited Numerical Precisioncited by 368
  23. 2019Variational Information Distillation for Knowledge Transfercited by 321
  24. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
  25. 2015Diffusion-Convolutional Neural Networkscited by 268
  26. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  27. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  28. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
  29. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  30. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  31. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  32. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  33. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  34. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  35. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  36. 2020Deep Visual Domain Adaptationcited by 91
  37. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  38. 2018Compressing Neural Networks using the Variational Information Bottleneckcited by 59

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.