mlsanityData to 7 Oct 2026

CKGConv: General Graph Convolution with Continuous Kernels

arXiv 2404.13604 ↗First posted 21 Apr 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https://github.com/networkslab/CKGConv.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 89 of its 103 references that are in the map. First posted on arXiv 21 Apr 2024.

Builds on

89 of 103 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2017Graph Attention Networkscited by 8,854
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2017Inductive Representation Learning on Large Graphscited by 6,284
  10. 2016Layer Normalizationcited by 5,579
  11. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  12. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
38 more
  1. 2018How Powerful are Graph Neural Networks?cited by 4,355
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  11. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  12. 2017Deep Setscited by 1,394
  13. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  14. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  15. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  16. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  17. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  18. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  19. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  20. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  21. 2020Benchmarking Graph Neural Networkscited by 672
  22. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  23. 2020A Generalization of Transformer Networks to Graphscited by 653
  24. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  25. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  26. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  27. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  28. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  29. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  30. 2019Diffusion Improves Graph Learningcited by 414
  31. 2021Early Convolutions Help Transformers See Bettercited by 395
  32. 2017Residual Gated Graph ConvNetscited by 341
  33. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  34. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  35. 2016Dynamic Filter Networkscited by 318
  36. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  37. 2022How Do Vision Transformers Work?cited by 305
  38. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Plain Transformers Can be Powerful Graph Learnerscited by 2
  2. 2025Generalizable Insights for Graph Transformers in Theory and Practicecited by 2
  3. 2025LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisationcited by 0
  4. 2026RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutionscited by 0