Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Hypergraph-enhanced Dual Semi-supervised Graph Classification (2405.04773v2)

Published 8 May 2024 in cs.LG, cs.AI, cs.IR, and cs.SI

Abstract: In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to model higher-order dependencies among nodes. To tackle these challenges, we propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification, which captures graph semantics from the perspective of the hypergraph and the line graph, respectively. Specifically, to better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies beyond pairwise relations. Meanwhile, based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges, thereby better mining the underlying semantic structures. Finally, we develop a relational consistency learning to facilitate knowledge transfer between the two branches and provide better mutual guidance. Extensive experiments on real-world graph datasets verify the effectiveness of the proposed method against existing state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Sub2vec: Feature learning for subgraphs. In Advances in Knowledge Discovery and Data Mining: 22nd Pacific-Asia Conference, PAKDD 2018, Melbourne, VIC, Australia, June 3-6, 2018, Proceedings, Part II 22, pp.  170–182. Springer, 2018.
  2. Protein function prediction via graph kernels. Bioinformatics, 21(suppl_1):i47–i56, 2005.
  3. Hypergraph structure learning for hypergraph neural networks. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp.  1923–1929, 2022.
  4. Nemofinder: Dissecting genome-wide protein-protein interactions with meso-scale network motifs. In Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.  106–115, 2006.
  5. Distinguishing enzyme structures from non-enzymes without alignments. Journal of Molecular Biology, 330(4):771–783, 2003.
  6. Knowledge hypergraphs: Prediction beyond binary relations. arXiv preprint arXiv:1906.00137, 2019.
  7. Hypergraph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp.  3558–3565, 2019.
  8. Neural message passing for quantum chemistry. In International Conference on Machine Learning, pp.  1263–1272. PMLR, 2017.
  9. Semi-supervised learning by entropy minimization. Advances in Neural Information Processing Systems, 17, 2004.
  10. Asgn: An active semi-supervised graph neural network for molecular property prediction. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.  731–752, 2020.
  11. Learning hypergraph-regularized attribute predictors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  409–417, 2015.
  12. Dynamic hypergraph neural networks. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pp.  2635–2641, 2019.
  13. Kgnn: Harnessing kernel-based networks for semi-supervised graph classification. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp.  421–429, 2022.
  14. Few-shot molecular property prediction via hierarchically structured learning on relation graphs. Neural Networks, 2023a.
  15. Tgnn: A joint semi-supervised framework for graph-level classification. arXiv preprint arXiv:2304.11688, 2023b.
  16. A comprehensive survey on deep graph representation learning. Neural Networks, pp.  106207, 2024a.
  17. A survey of data-efficient graph learning. arXiv preprint arXiv:2402.00447, 2024b.
  18. Marginalized kernels between labeled graphs. In Proceedings of International Conference on Machine Learning, pp.  321–328, 2003.
  19. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  20. kgcn: a graph-based deep learning framework for chemical structures. Journal of Cheminformatics, 12:1–10, 2020.
  21. Temporal ensembling for semi-supervised learning. In Proceedings of International Conference on Learning Representations, 2017.
  22. Semi-supervised graph classification: A hierarchical graph perspective. In The World Wide Web Conference, pp.  972–982, 2019.
  23. Barely-supervised learning: Semi-supervised learning with very few labeled images. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  1881–1889, 2022.
  24. Dualgraph: Improving semi-supervised graph classification via dual contrastive learning. In 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp.  699–712. IEEE, 2022.
  25. Towards effective semi-supervised node classification with hybrid curriculum pseudo-labeling. ACM Transactions on Multimedia Computing, Communications and Applications, 2023a.
  26. Rignn: A rationale perspective for semi-supervised open-world graph classification. Transactions on Machine Learning Research, 2023b.
  27. Towards semi-supervised universal graph classification. IEEE Transactions on Knowledge and Data Engineering, 2023c.
  28. Rahnet: Retrieval augmented hybrid network for long-tailed graph classification. In Proceedings of the 31st ACM International Conference on Multimedia, pp.  3817–3826, 2023.
  29. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8):1979–1993, 2018.
  30. graph2vec: Learning distributed representations of graphs. arXiv preprint arXiv:1707.05005, 2017.
  31. Propagation kernels: efficient graph kernels from propagated information. Machine Learning, 102(2):209–245, 2016.
  32. Learning graph ode for continuous-time sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, 2024.
  33. Efficient graphlet kernels for large graph comparison. In Proceedings of International Conference on Artificial Intelligence and Statistics, pp.  488–495, 2009.
  34. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research, 12(9):2539–2561, 2011.
  35. Graph-based semi-supervised learning. Springer Nature, 2022.
  36. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In Proceedings of International Conference on Learning Representations, 2020.
  37. Heterogeneous hypergraph embedding for graph classification. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp.  725–733, 2021.
  38. Hypergraph clustering based on pagerank. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.  1970–1978, 2020.
  39. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems, pp.  1195–1204, 2017.
  40. Contrastive and generative graph convolutional networks for graph-based semi-supervised learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  10049–10057, 2021.
  41. Visual classification by ℓ1subscriptℓ1\ell_{1}roman_ℓ start_POSTSUBSCRIPT 1 end_POSTSUBSCRIPT-hypergraph modeling. IEEE Transactions on Knowledge and Data Engineering, 27(9):2564–2574, 2015.
  42. Whitney, H. Congruent graphs and the connectivity of graphs. Hassler Whitney Collected Papers, pp.  61–79, 1992.
  43. Self-supervised hypergraph convolutional networks for session-based recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  4503–4511, 2021.
  44. Dynamic-group-aware networks for multi-agent trajectory prediction with relational reasoning. Neural Networks, 170:564–577, 2024.
  45. How powerful are graph neural networks? In Proceedings of International Conference on Learning Representations, 2019.
  46. Nhp: Neural hypergraph link prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp.  1705–1714, 2020.
  47. Deep graph kernels. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.  1365–1374, 2015.
  48. Redundancy-free self-supervised relational learning for graph clustering. IEEE Transactions on Neural Networks and Learning Systems, 2023a.
  49. Towards long-tailed recognition for graph classification via collaborative experts. IEEE Transactions on Big Data, 2023b.
  50. Graph contrastive learning with augmentations. Advances in Neural Information Processing Systems, 33:5812–5823, 2020.
  51. Graph contrastive learning automated. In International Conference on Machine Learning, pp.  12121–12132. PMLR, 2021.
  52. Adaptive hypergraph learning and its application in image classification. IEEE Transactions on Image Processing, 21(7):3262–3272, 2012.
  53. Alex: Towards effective graph transfer learning with noisy labels. In Proceedings of the 31st ACM International Conference on Multimedia, pp.  3647–3656, 2023.
  54. Link prediction based on graph neural networks. Advances in Neural Information Processing Systems, 31, 2018.
  55. Deep hypergraph structure learning. arXiv preprint arXiv:2208.12547, 2022.
Citations (4)
View on Semantic Scholar

Summary

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

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

Tweets