mlsanityData to 7 Oct 2026

Improving Graph Neural Networks with Learnable Propagation Operators

arXiv 2210.17224 ↗First posted 31 Oct 2022cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are limited in their propagation operators. In many cases, these operators often contain non-negative elements only and are shared across channels, limiting the expressiveness of GNNs. Moreover, some GNNs suffer from over-smoothing, limiting their depth. On the other hand, Convolutional Neural Networks (CNNs) can learn diverse propagation filters, and phenomena like over-smoothing are typically not apparent in CNNs. In this paper, we bridge these gaps by incorporating trainable channel-wise weighting factors ω to learn and mix multiple smoothing and sharpening propagation operators at each layer. Our generic method is called ωGNN, and is easy to implement. We study two variants: ωGCN and ωGAT. For ωGCN, we theoretically analyse its behaviour and the impact of ω on the obtained node features. Our experiments confirm these findings, demonstrating and explaining how both variants do not over-smooth. Additionally, we experiment with 15 real-world datasets on node- and graph-classification tasks, where our ωGCN and ωGAT perform on par with state-of-the-art methods.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 69 of its 91 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

69 of 91 references.

References · 69

  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. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  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. 2022A ConvNet for the 2020scited by 3,545
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  9. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  10. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  11. 2020Simple and Deep Graph Convolutional Networkscited by 857
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  13. 2021How Attentive are Graph Attention Networks?cited by 818
  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. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  17. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  18. 2019Multi-scale Attributed Node Embeddingcited by 543
  19. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  20. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  21. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  22. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  23. 2019Diffusion Improves Graph Learningcited by 414
  24. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  25. 2018Invariant and Equivariant Graph Networkscited by 339
  26. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  27. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  28. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  29. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  30. 2021GRAND: Graph Neural Diffusioncited by 258
  31. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 245
  32. 2021Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networkscited by 219
  33. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  34. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  35. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
  36. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  37. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 190
  38. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 4; 2026: 2.

19 papers.

Sort:

By area:

  1. 2024Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networkscited by 10
  2. 2023Are GATs Out of Balance?cited by 9
  3. 2024Redesigning graph filter-based GNNs to relax the homophily assumptioncited by 8
  4. 2024Representation Learning on Heterophilic Graph with Directional Neighborhood Attentioncited by 6
  5. 2024Graph Neural Reaction Diffusion Modelscited by 6
  6. 2024Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graphcited by 6
  7. 2025Improving the Effective Receptive Field of Message-Passing Neural Networkscited by 6
  8. 2024MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networkscited by 5
  9. 2024GATE: How to Keep Out Intrusive Neighborscited by 4
  10. 2024Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learningcited by 3
  11. 2024Quadratic Binary Optimization with Graph Neural Networkscited by 2
  12. 2024Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspectivecited by 2
7 more
  1. 2025A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNscited by 2
  2. 2024GTAGCN: Generalized Topology Adaptive Graph Convolutional Networkscited by 1
  3. 2024First-order PDES for Graph Neural Networks: Advection And Burgers Equation Modelscited by 0
  4. 2025Personalized Layer Selection for Graph Neural Networkscited by 0
  5. 2025Simplifying Graph Convolutional Networks with Redundancy-Free Neighborscited by 0
  6. 2026Learning from Historical Activations in Graph Neural Networkscited by 0
  7. 2026Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNscited by 0