mlsanityData to 7 Oct 2026

pathGCN: Learning General Graph Spatial Operators from Paths

arXiv 2207.07408 ↗First posted 15 Jul 2022cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs), similarly to Convolutional Neural Networks (CNNs), are typically based on two main operations - spatial and point-wise convolutions. In the context of GCNs, differently from CNNs, a pre-determined spatial operator based on the graph Laplacian is often chosen, allowing only the point-wise operations to be learnt. However, learning a meaningful spatial operator is critical for developing more expressive GCNs for improved performance. In this paper we propose pathGCN, a novel approach to learn the spatial operator from random paths on the graph. We analyze the convergence of our method and its difference from existing GCNs. Furthermore, we discuss several options of combining our learnt spatial operator with point-wise convolutions. Our extensive experiments on numerous datasets suggest that by properly learning both the spatial and point-wise convolutions, phenomena like over-smoothing can be inherently avoided, and new state-of-the-art performance is achieved.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 47 of its 60 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

47 of 60 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Graph Attention Networkscited by 8,854
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2018How Powerful are Graph Neural Networks?cited by 4,355
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  12. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
35 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  10. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  11. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  12. 2020Simple and Deep Graph Convolutional Networkscited by 857
  13. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  14. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  15. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  16. 2019Multi-scale Attributed Node Embeddingcited by 543
  17. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  18. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  19. 2019Diffusion Improves Graph Learningcited by 414
  20. 2018Invariant and Equivariant Graph Networkscited by 339
  21. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  22. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  23. 2021GRAND: Graph Neural Diffusioncited by 258
  24. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  25. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  26. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  27. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  28. 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
  29. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  30. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  31. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  32. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  33. 2020Path Integral Based Convolution and Pooling for Graph Neural Networkscited by 35
  34. 2020DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Poolingcited by 16
  35. 2019LeanConvNets: Low-cost Yet Effective Convolutional Neural Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 4; 2025: 1; 2026: 2.

15 papers.

Sort:

  1. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 58
  2. 2022Improving Graph Neural Networks with Learnable Propagation Operatorscited by 19
  3. 2023Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexescited by 10
  4. 2023Are GATs Out of Balance?cited by 9
  5. 2022Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networkscited by 4
  6. 2023Improving Subgraph-GNNs via Edge-Level Ego-Network Encodingscited by 4
  7. 2024Global-Local Graph Neural Networks for Node-Classificationcited by 4
  8. 2024Scalable Graph Compressed Convolutionscited by 2
  9. 2022Every Node Counts: Improving the Training of Graph Neural Networks on Node Classificationcited by 1
  10. 2023Multi-Temporal Relationship Inference in Urban Areascited by 1
  11. 2024Learning From Simplicial Data Based on Random Walks and 1D Convolutionscited by 0
  12. 2024Information propagation dynamics in Deep Graph Networkscited by 0
3 more
  1. 2025LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisationcited by 0
  2. 2026Learning from Historical Activations in Graph Neural Networkscited by 0
  3. 2026Diffusion Attention Expert Model for Predicting and Semi-automatic Localizing STAS in Lung Cancer Histopathological Imagescited by 0