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

L^2GC:Lorentzian Linear Graph Convolutional Networks for Node Classification (2403.06064v3)

Published 10 Mar 2024 in cs.LG, cs.AI, and cs.CL

Abstract: Linear Graph Convolutional Networks (GCNs) are used to classify the node in the graph data. However, we note that most existing linear GCN models perform neural network operations in Euclidean space, which do not explicitly capture the tree-like hierarchical structure exhibited in real-world datasets that modeled as graphs. In this paper, we attempt to introduce hyperbolic space into linear GCN and propose a novel framework for Lorentzian linear GCN. Specifically, we map the learned features of graph nodes into hyperbolic space, and then perform a Lorentzian linear feature transformation to capture the underlying tree-like structure of data. Experimental results on standard citation networks datasets with semi-supervised learning show that our approach yields new state-of-the-art results of accuracy 74.7$\%$ on Citeseer and 81.3$\%$ on PubMed datasets. Furthermore, we observe that our approach can be trained up to two orders of magnitude faster than other nonlinear GCN models on PubMed dataset. Our code is publicly available at https://github.com/llqy123/LLGC-master.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Fully linear graph convolutional networks for semi-supervised and unsupervised classification. ACM Transactions on Intelligent Systems and Technology, 14(3):1–23.
  2. Hyperbolic graph convolutional neural networks. Advances in neural information processing systems, 32:4869–4880.
  3. Fully hyperbolic neural networks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5672–5686.
  4. Hierarchical structure and the prediction of missing links in networks. Nature, 453(7191):98–101.
  5. Graph neural networks with global noise filtering for session-based recommendation. Neurocomputing, 472:113–123.
  6. Sign: Scalable inception graph neural networks. arXiv preprint arXiv:2004.11198.
  7. Hyperbolic neural networks. In Advances in neural information processing systems, pages 5345–5355.
  8. Predict then propagate: Graph neural networks meet personalized pagerank. In International Conference on Learning Representations (ICLR).
  9. Hyperbolic attention networks. arXiv preprint arXiv:1805.09786.
  10. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  11. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR).
  12. Chang Li and Dan Goldwasser. 2019. Encoding social information with graph convolutional networks forpolitical perspective detection in news media. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2594–2604.
  13. G22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTCN: Graph gaussian convolution networks with concentrated graph filters. In International Conference on Machine Learning, pages 12782–12796. PMLR.
  14. Enhancing hyperbolic graph embeddings via contrastive learning. arXiv preprint arXiv:2201.08554.
  15. Hyperbolic graph neural networks. Advances in neural information processing systems, 32.
  16. Elastic graph neural networks. In International Conference on Machine Learning, pages 6837–6849. PMLR.
  17. Self-consistent graph neural networks for semi-supervised node classification. IEEE Transactions on Big Data.
  18. Machine learning meets complex networks via coalescent embedding in the hyperbolic space. Nature communications, 8(1):1615.
  19. Maximillian Nickel and Douwe Kiela. 2018. Learning continuous hierarchies in the lorentz model of hyperbolic geometry. In International conference on machine learning, pages 3779–3788. PMLR.
  20. Graph neural networks for friend ranking in large-scale social platforms. In Proceedings of the Web Conference 2021, pages 2535–2546.
  21. Collective classification in network data. AI magazine, 29(3):93–93.
  22. Gamenet: Graph augmented memory networks for recommending medication combination. In proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 1126–1133.
  23. Dependency-driven relation extraction with attentive graph convolutional networks. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4458–4471.
  24. Poincaré glove: Hyperbolic word embeddings. ArXiv, abs/1810.06546.
  25. Graph attention networks. In International Conference on Learning Representations (ICLR).
  26. Self-supervised adversarial distribution regularization for medication recommendation. In IJCAI, pages 3134–3140.
  27. Dissecting the diffusion process in linear graph convolutional networks. Advances in Neural Information Processing Systems, 34:5758–5769.
  28. Thomas James Willmore. 2013. An introduction to differential geometry. Courier Corporation.
  29. Simplifying graph convolutional networks. In International conference on machine learning, pages 6861–6871. PMLR.
  30. Graph convolutional networks using heat kernel for semi-supervised learning. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pages 1928–1934.
  31. Graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 7370–7377.
  32. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 974–983.
  33. Hyperbolic graph attention network. IEEE Transactions on Big Data, 8(6):1690–1701.
  34. Lorentzian graph convolutional networks. In Proceedings of the Web Conference 2021, pages 1249–1261.
Citations (3)
View on Semantic Scholar

Summary

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

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