mlsanityData to 14 Oct 2026

Graph Anisotropic Diffusion

arXiv 2205.00354 ↗First posted 30 Apr 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional Graph Neural Networks (GNNs) rely on message passing, which amounts to permutation-invariant local aggregation of neighbour features. Such a process is isotropic and there is no notion of `direction' on the graph. We present a new GNN architecture called Graph Anisotropic Diffusion. Our model alternates between linear diffusion, for which a closed-form solution is available, and local anisotropic filters to obtain efficient multi-hop anisotropic kernels. We test our model on two common molecular property prediction benchmarks (ZINC and QM9) and show its competitive performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 30 Apr 2022.

Builds on

42 of 59 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  10. 2019Graph Neural Networks for Social Recommendationcited by 714
  11. 2020Benchmarking Graph Neural Networkscited by 680
  12. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
30 more
  1. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  2. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  3. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  4. 2019Diffusion Improves Graph Learningcited by 414
  5. 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 349
  6. 2017Residual Gated Graph ConvNetscited by 346
  7. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  8. 2021GRAND: Graph Neural Diffusioncited by 258
  9. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  10. 2021Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networkscited by 221
  11. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  12. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  13. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 164
  14. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 161
  15. 2019Graph Neural Ordinary Differential Equationscited by 154
  16. 2020Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Predictioncited by 138
  17. 2020Directional Graph Networkscited by 133
  18. 2019Continuous Graph Neural Networkscited by 114
  19. 2019Hamiltonian Graph Networks with ODE Integratorscited by 108
  20. 2020Implicit Graph Neural Networkscited by 100
  21. 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 97
  22. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  23. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  24. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  25. 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 64
  26. 2020Hierarchical Inter-Message Passing for Learning on Molecular Graphscited by 59
  27. 2019Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Moleculescited by 28
  28. 2020Utilising Graph Machine Learning within Drug Discovery and Developmentcited by 26
  29. 2021Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Predictioncited by 24
  30. 2019Discrete and Continuous Deep Residual Learning Over Graphscited by 13

Built on by

Not cited yet.