Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
46 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

Deep Contrastive Graph Learning with Clustering-Oriented Guidance (2402.16012v1)

Published 25 Feb 2024 in cs.LG and cs.AI

Abstract: Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. To handle the general clustering scenario without a prior graph, these models estimate an initial graph beforehand to apply GCN. Throughout the literature, we have witnessed that 1) most models focus on the initial graph while neglecting the original features. Therefore, the discriminability of the learned representation may be corrupted by a low-quality initial graph; 2) the training procedure lacks effective clustering guidance, which may lead to the incorporation of clustering-irrelevant information into the learned graph. To tackle these problems, the Deep Contrastive Graph Learning (DCGL) model is proposed for general data clustering. Specifically, we establish a pseudo-siamese network, which incorporates auto-encoder with GCN to emphasize both the graph structure and the original features. On this basis, feature-level contrastive learning is introduced to enhance the discriminative capacity, and the relationship between samples and centroids is employed as the clustering-oriented guidance. Afterward, a two-branch graph learning mechanism is designed to extract the local and global structural relationships, which are further embedded into a unified graph under the cluster-level contrastive guidance. Experimental results on several benchmark datasets demonstrate the superiority of DCGL against state-of-the-art algorithms.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Structural deep clustering network. In Proceedings of the Web Conference 2020, 1400–1410.
  2. Graph regularized nonnegative matrix factorization for data representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8): 1548–1560.
  3. Entropy minimizing matrix factorization. IEEE Transactions on Neural Networks and Learning Systems, 34(11): 9209–9222.
  4. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning, 1597–1607.
  5. Iterative deep graph learning for graph neural networks: Better and robust node embeddings. Advances in Neural Information Processing Systems, 33: 19314–19326.
  6. Sparse subspace clustering: Algorithm, theory, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11): 2765–2781.
  7. Algorithm AS 136: A k-means clustering algorithm. Journal of the Royal Statistical Society: Series C (applied statistics), 28(1): 100–108.
  8. Contrastive multi-view representation learning on graphs. In International Conference on Machine Learning, 4116–4126.
  9. Multi-view subspace clustering on topological manifold. Advances in Neural Information Processing Systems, 35: 25883–25894.
  10. Semi-supervised learning with graph learning-convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11313–11320.
  11. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 66–74.
  12. Robust graph learning from noisy data. IEEE Transactions on Cybernetics, 50(5): 1833–1843.
  13. Twin learning for similarity and clustering: A unified kernel approach. In Proceedings of the AAAI Conference on Artificial Intelligence, 2080–2086.
  14. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  15. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  16. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308.
  17. Robust nonnegative matrix factorization using l21-norm. In Proceedings of the 20th ACM International Conference on Information and Knowledge Management, 673–682.
  18. Li, X. 2022a. Multi-modal cognitive computing. SCIENTIA SINICA Informationis, 53(1): 1–32.
  19. Li, X. 2022b. Vicinagearth security. Communication of the CCF, 18(11): 44–52.
  20. Locality adaptive discriminant analysis. In International Joint Conference on Artificial Intelligence, 2201–2207.
  21. A multiview-based parameter free framework for group detection. In Proceedings of the AAAI Conference on Artificial Intelligence, 4147–4153.
  22. Adaptive graph auto-encoder for general data clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12): 9725–9732.
  23. Multilayer graph contrastive clustering network. Information Sciences, 613: 256–267.
  24. A survey of deep graph clustering: Taxonomy, challenge, and application. arXiv preprint arXiv:2211.12875.
  25. Deep graph clustering via dual correlation reduction. In Proceedings of the AAAI Conference on Artificial Intelligence, 7603–7611.
  26. Simple contrastive graph clustering. IEEE Transactions on Neural Networks and Learning Systems.
  27. Towards unsupervised deep graph structure learning. In Proceedings of the Web Conference 2022, 1392–1403.
  28. Simple unsupervised graph representation learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 7797–7805.
  29. Clustering and projected clustering with adaptive neighbors. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 977–986.
  30. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748.
  31. Deep clustering: A comprehensive survey. arXiv preprint arXiv:2210.04142.
  32. SpectralNet: Spectral clustering using deep neural networks. arXiv preprint arXiv:1801.01587.
  33. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8): 888–905.
  34. Graph structure learning with variational information bottleneck. In Proceedings of the AAAI Conference on Artificial Intelligence, 4165–4174.
  35. Sample-level multi-view graph clustering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 23966–23975.
  36. Deep fusion clustering network. In Proceedings of the AAAI Conference on Artificial Intelligence, 9978–9987.
  37. Visualizing data using t-SNE. Journal of Machine Learning Research, 9(11).
  38. Attributed graph clustering: A deep attentional embedding approach. In International Joint Conference on Artificial Intelligence, 3670–3676.
  39. Unsupervised deep embedding for clustering analysis. In International Conference on Machine Learning, 478–487.
  40. Cluster-guided contrastive graph clustering network. In Proceedings of the AAAI Conference on Artificial Intelligence, 10834–10842.
  41. Graph-revised convolutional network. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 378–393.
  42. Self-tuning spectral clustering. Advances in Neural Information Processing Systems, 17.
  43. Non-graph data clustering via O⁢(n)𝑂𝑛O(n)italic_O ( italic_n ) bipartite graph convolution. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  44. Graph debiased contrastive learning with joint representation clustering. In International Joint Conference on Artificial Intelligence, 3434–3440.
  45. Adaptive graph convolutional clustering network with optimal probabilistic graph. Neural Networks, 156: 271–284.
  46. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021, 2069–2080.
Citations (2)
View on Semantic Scholar

Summary

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

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