Papers
Topics
Authors
Recent
Search
2000 character limit reached

LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity

Published 7 May 2023 in cs.LG and cs.AI | (2305.04225v2)

Abstract: Heterophily has been considered as an issue that hurts the performance of Graph Neural Networks (GNNs). To address this issue, some existing work uses a graph-level weighted fusion of the information of multi-hop neighbors to include more nodes with homophily. However, the heterophily might differ among nodes, which requires to consider the local topology. Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module. For better fusion, we propose a novel and efficient Initial Residual Difference Connection (IRDC) to extract more informative multi-hop information. Moreover, we provide theoretical analysis on the effectiveness of LocalSim representing node homophily on synthetic graphs. Extensive evaluations over real benchmark datasets show that our proposed method, namely Local Similarity Graph Neural Network (LSGNN), can offer comparable or superior state-of-the-art performance on both homophilic and heterophilic graphs. Meanwhile, the plug-and-play model can significantly boost the performance of existing GNNs. Our code is provided at https://github.com/draym28/LSGNN.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In international conference on machine learning, pages 21–29. PMLR, 2019.
  2. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261, 2018.
  3. Beyond low-frequency information in graph convolutional networks. arXiv preprint arXiv:2101.00797, 2021.
  4. Simplified graph convolution with heterophily. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho, editors, Advances in Neural Information Processing Systems, 2022.
  5. Simple and deep graph convolutional networks. In International Conference on Machine Learning, pages 1725–1735. PMLR, 2020.
  6. Adaptive universal generalized pagerank graph neural network. In International Conference on Learning Representations. https://openreview. net/forum, 2021.
  7. Convolutional neural networks on graphs with fast localized spectral filtering. arXiv, abs/1606.09375, 2016.
  8. A fair comparison of graph neural networks for graph classification. In ICLR. OpenReview.net, 2020.
  9. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997, 2018.
  10. Lise Getoor. Query-driven active surveying for collective classification. 2012.
  11. Inductive representation learning on large graphs. arXiv, abs/1706.02216, 2017.
  12. William L Hamilton. Graph representation learning. Synthesis Lectures on Artifical Intelligence and Machine Learning, 14(3):1–159, 2020.
  13. Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. Advances in Neural Information Processing Systems, 34, 2021.
  14. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118–22133, 2020.
  15. Assortative mating in animals. The American Naturalist, 181(6):E125–E138, 2013.
  16. Semi-supervised classification with graph convolutional networks. arXiv, abs/1609.02907, 2016.
  17. Finding global homophily in graph neural networks when meeting heterophily. arXiv preprint arXiv:2205.07308, 2022.
  18. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Advances in Neural Information Processing Systems, 34:20887–20902, 2021.
  19. Towards deeper graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 338–348, 2020.
  20. Revisiting heterophily for graph neural networks. arXiv preprint arXiv:2210.07606, 2022.
  21. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415–444, 2001.
  22. The pagerank citation ranking: Bringing order to the web. Technical report, Stanford infolab, 1999.
  23. Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287, 2020.
  24. Multi-Scale Attributed Node Embedding. Journal of Complex Networks, 9(2), 2021.
  25. The graph neural network model. IEEE transactions on neural networks, 20(1):61–80, 2008.
  26. Collective classification in network data. Ai Magazine, 2008.
  27. Graph attention networks. arXiv, abs/1710.10903, 2017.
  28. Simplifying graph convolutional networks. arXiv preprint arXiv:1902.07153, 2019.
  29. Difference residual graph neural networks. In Proceedings of the 30th ACM International Conference on Multimedia, pages 3356–3364, 2022.
  30. Link prediction based on graph neural networks. In NeurIPS, pages 5171–5181, 2018.
  31. Graph neural networks with heterophily. arXiv preprint arXiv:2009.13566, 2020.
  32. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems, 33, 2020.
Citations (9)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up