mlsanityData to 14 Oct 2026

Unified GCNs: Towards Connecting GCNs with CNNs

arXiv 2204.12300 ↗First posted 26 Apr 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs) have been widely demonstrated their powerful ability in graph data representation and learning. Existing graph convolution layers are mainly designed based on graph signal processing and transform aspect which usually suffer from some limitations, such as over-smoothing, over-squashing and non-robustness, etc. As we all know that Convolution Neural Networks (CNNs) have received great success in many computer vision and machine learning. One main aspect is that CNNs leverage many learnable convolution filters (kernels) to obtain rich feature descriptors and thus can have high capacity to encode complex patterns in visual data analysis. Also, CNNs are flexible in designing their network architecture, such as MobileNet, ResNet, Xception, etc. Therefore, it is natural to arise a question: can we design graph convolutional layer as flexibly as that in CNNs? Innovatively, in this paper, we consider connecting GCNs with CNNs deeply from a general perspective of depthwise separable convolution operation. Specifically, we show that GCN and GAT indeed perform some specific depthwise separable convolution operations. This novel interpretation enables us to better understand the connections between GCNs (GCN, GAT) and CNNs and further inspires us to design more Unified GCNs (UGCNs). As two showcases, we implement two UGCNs, i.e., Separable UGCN (S-UGCN) and General UGCN (G-UGCN) for graph data representation and learning. Promising experiments on several graph representation benchmarks demonstrate the effectiveness and advantages of the proposed UGCNs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

44 of 63 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Inductive Representation Learning on Large Graphscited by 6,320
  7. 2018How Powerful are Graph Neural Networks?cited by 4,393
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  10. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  11. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  12. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
32 more
  1. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  2. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  3. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  5. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  6. 2019Panoptic Feature Pyramid Networkscited by 645
  7. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 586
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  10. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  11. 2019GhostNet: More Features from Cheap Operationscited by 410
  12. 2016Learning Convolutional Neural Networks for Graphscited by 314
  13. 2022UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learningcited by 184
  14. 2017Understanding Convolution for Semantic Segmentationcited by 168
  15. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  16. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  17. 2019Graph Wavelet Neural Networkcited by 131
  18. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  19. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 118
  20. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  21. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  22. 2019Transferability of Spectral Graph Convolutional Neural Networkscited by 92
  23. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  24. 2020Factorizable Graph Convolutional Networkscited by 79
  25. 2021On the Connection between Local Attention and Dynamic Depth-wise Convolutioncited by 62
  26. 2020Wasserstein Embedding for Graph Learningcited by 56
  27. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  28. 2018Graph Capsule Convolutional Neural Networkscited by 27
  29. 2020GraphCL: Contrastive Self-Supervised Learning of Graph Representationscited by 26
  30. 2019Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservationcited by 17
  31. 2019Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classificationcited by 13
  32. 2019DAGCN: Dual Attention Graph Convolutional Networkscited by 9

Built on by

Not cited yet.