Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering (2312.14438v1)

Published 22 Dec 2023 in cs.LG, cs.AI, and cs.SI

Abstract: Recently, many carefully crafted graph representation learning methods have achieved impressive performance on either strong heterophilic or homophilic graphs, but not both. Therefore, they are incapable of generalizing well across real-world graphs with different levels of homophily. This is attributed to their neglect of homophily in heterophilic graphs, and vice versa. In this paper, we propose a two-fold filtering mechanism to extract homophily in heterophilic graphs and vice versa. In particular, we extend the graph heat equation to perform heterophilic aggregation of global information from a long distance. The resultant filter can be exactly approximated by the Possion-Charlier (PC) polynomials. To further exploit information at multiple orders, we introduce a powerful graph convolution PC-Conv and its instantiation PCNet for the node classification task. Compared with state-of-the-art GNNs, PCNet shows competitive performance on well-known homophilic and heterophilic graphs. Our implementation is available at https://github.com/uestclbh/PC-Conv.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In International Conference on Machine Learning, 21–29. PMLR.
  2. Analyzing the expressive power of graph neural networks in a spectral perspective. In International Conference on Learning Representations.
  3. Graph Neural Networks with convolutional ARMA filters. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  4. Simple and deep graph convolutional networks. In International Conference on Machine Learning, 1725–1735. PMLR.
  5. Adaptive Universal Generalized PageRank Graph Neural Network. In International Conference on Learning Representations.
  6. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In Advances in Neural Information Processing Systems, 3837–3845.
  7. Pde-gcn: Novel architectures for graph neural networks motivated by partial differential equations. Advances in Neural Information Processing Systems, 34: 3836–3849.
  8. Structure-preserving graph representation learning. In 2022 IEEE International Conference on Data Mining (ICDM), 927–932. IEEE.
  9. p𝑝pitalic_p-Laplacian Based Graph Neural Networks. In International Conference on Machine Learning, 6878–6917. PMLR.
  10. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30.
  11. Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited. Advances in Neural Information Processing Systems.
  12. Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. Advances in Neural Information Processing Systems, 34: 14239–14251.
  13. Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD), KDD ’22, 709–719. Association for Computing Machinery.
  14. Predict then Propagate: Graph Neural Networks meet Personalized PageRank. In International Conference on Learning Representations.
  15. Diffusion improves graph learning. Advances in Neural Information Processing Systems.
  16. Heat kernel based community detection. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 1386–1395.
  17. Kroeker, J. 1977. Wiener analysis of nonlinear systems using Poisson-Charlier crosscorrelation. Biological Cybernetics, 27(4): 221–227.
  18. EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks. Advances in Neural Information Processing Systems.
  19. Finding Global Homophily in Graph Neural Networks When Meeting Heterophily. In International Conference on Machine Learning. PMLR.
  20. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Advances in Neural Information Processing Systems, 34: 20887–20902.
  21. Self-supervised consensus representation learning for attributed graph. In Proceedings of the 29th ACM international conference on multimedia, 2654–2662.
  22. Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? arXiv preprint arXiv:2109.05641.
  23. Revisiting heterophily for graph neural networks. Advances in neural information processing systems, 35: 1362–1375.
  24. Break the ceiling: Stronger multi-scale deep graph convolutional networks. Advances in neural information processing systems, 32.
  25. Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks. In NeurIPS 2022 Workshop: New Frontiers in Graph Learning.
  26. Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? Advances in neural information processing systems.
  27. Birds of a feather: Homophily in social networks. Annual review of sociology, 415–444.
  28. Multi-view contrastive graph clustering. Advances in neural information processing systems, 34: 2148–2159.
  29. Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering. In International Conference on Machine Learning. PMLR.
  30. Geom-GCN: Geometric Graph Convolutional Networks. In International Conference on Learning Representations.
  31. Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
  32. Truesdell, C. 1947. A Note on the Poisson-Charlier Functions. The Annals of Mathematical Statistics, 18(3): 450–454.
  33. Graph Attention Networks. In International Conference on Learning Representations.
  34. How Powerful are Spectral Graph Neural Networks. In International Conference on Machine Learning, 23341–23362. PMLR.
  35. Dissecting the diffusion process in linear graph convolutional networks. Advances in Neural Information Processing Systems, 34: 5758–5769.
  36. Weber, A. 2010. Analysis of the physical Laplacian and the heat flow on a locally finite graph. Journal of Mathematical Analysis and Applications, 1(370): 146–158.
  37. Semi-supervised classification with graph convolutional networks. In J. International Conference on Learning Representations (ICLR 2017).
  38. Simplifying graph convolutional networks. In International Conference on Machine Learning, 6861–6871. PMLR.
  39. Contrastive graph clustering with adaptive filter. Expert Systems with Applications, 219: 119645.
  40. Graph convolutional networks using heat kernel for semi-supervised learning. In IJCAI.
  41. Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks. In 2022 IEEE International Conference on Data Mining. IEEE.
  42. A new perspective on the effects of spectrum in graph neural networks. In International Conference on Machine Learning, 25261–25279. PMLR.
  43. Graph neural networks inspired by classical iterative algorithms. In International Conference on Machine Learning, 11773–11783. PMLR.
  44. Revisiting semi-supervised learning with graph embeddings. In International Conference on Machine Learning, 40–48. PMLR.
  45. NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning. In Proceedings of the 39th International Conference on Machine Learning, volume 162, 26467–26483. PMLR.
  46. Node dependent local smoothing for scalable graph learning. Advances in Neural Information Processing Systems, 34: 20321–20332.
  47. Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs. In International Conference on Machine Learning. PMLR.
  48. Dirichlet energy constrained learning for deep graph neural networks. Advances in Neural Information Processing Systems, 34: 21834–21846.
  49. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems, 33: 7793–7804.
  50. Interpreting and Unifying Graph Neural Networks with An Optimization Framework. In The Web Conference, 1215–1226.
Citations (18)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - uestclbh/PC-Conv (7 stars)