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

DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (2312.12697v1)

Published 20 Dec 2023 in cs.LG and cs.SI

Abstract: Graph clustering is a fundamental and challenging task in the field of graph mining where the objective is to group the nodes into clusters taking into consideration the topology of the graph. It has several applications in diverse domains spanning social network analysis, recommender systems, computer vision, and bioinformatics. In this work, we propose a novel method, DGCluster, which primarily optimizes the modularity objective using graph neural networks and scales linearly with the graph size. Our method does not require the number of clusters to be specified as a part of the input and can also leverage the availability of auxiliary node level information. We extensively test DGCluster on several real-world datasets of varying sizes, across multiple popular cluster quality metrics. Our approach consistently outperforms the state-of-the-art methods, demonstrating significant performance gains in almost all settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Dfuzzy: a deep learning-based fuzzy clustering model for large graphs. Knowledge and Information Systems, 57: 159–181.
  2. Spectral clustering with graph neural networks for graph pooling. In International Conference on Machine Learning, 874–883. PMLR.
  3. Fast unfolding of communities in large networks. Journal of statistical mechanics: theory and experiment, 2008(10): P10008.
  4. Structural deep clustering network. In Proceedings of the web conference 2020, 1400–1410.
  5. Maximizing modularity is hard. arXiv preprint physics/0608255.
  6. Learning community structure with variational autoencoder. In 2018 IEEE international conference on data mining (ICDM), 69–78. IEEE.
  7. Efficient graph-based image segmentation. International journal of computer vision, 59: 167–181.
  8. Community detection in networks: A user guide. Physics reports, 659: 1–44.
  9. Clustering by passing messages between data points. science, 315(5814): 972–976.
  10. Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
  11. Algorithm AS 136: A k-means clustering algorithm. Journal of the royal statistical society. series c (applied statistics), 28(1): 100–108.
  12. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  13. Self-normalizing neural networks. Advances in neural information processing systems, 30.
  14. SCGC: Self-supervised contrastive graph clustering. arXiv preprint arXiv:2204.12656.
  15. Simple contrastive graph clustering. IEEE Transactions on Neural Networks and Learning Systems.
  16. Consensus community detection in multilayer networks using parameter-free graph pruning. In Advances in Knowledge Discovery and Data Mining: 22nd Pacific-Asia Conference, PAKDD 2018, Melbourne, VIC, Australia, June 3-6, 2018, Proceedings, Part III 22, 193–205. Springer.
  17. An effective trust-based recommendation method using a novel graph clustering algorithm. Physica A: Statistical mechanics and its applications, 436: 462–481.
  18. Newman, M. E. 2006a. Finding community structure in networks using the eigenvectors of matrices. Physical review E, 74(3): 036104.
  19. Newman, M. E. 2006b. Modularity and community structure in networks. Proceedings of the national academy of sciences, 103(23): 8577–8582.
  20. Mixing patterns and community structure in networks. In Statistical mechanics of complex networks, 66–87. Springer.
  21. Symmetric graph convolutional autoencoder for unsupervised graph representation learning. In Proceedings of the IEEE/CVF international conference on computer vision, 6519–6528.
  22. Peixoto, T. P. 2014. Efficient Monte Carlo and greedy heuristic for the inference of stochastic block models. Physical Review E, 89(1): 012804.
  23. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 701–710.
  24. The graph neural network model. IEEE transactions on neural networks, 20(1): 61–80.
  25. Collective classification in network data. AI magazine, 29(3): 93–93.
  26. Overlapping community detection with graph neural networks. arXiv preprint arXiv:1909.12201.
  27. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868.
  28. Normalized cuts and image segmentation. IEEE Transactions on pattern analysis and machine intelligence, 22(8): 888–905.
  29. Graph neural network encoding for community detection in attribute networks. IEEE Transactions on Cybernetics, 52(8): 7791–7804.
  30. Graph clustering with graph neural networks. Journal of Machine Learning Research, 24(127): 1–21.
  31. Graph attention networks. stat, 1050(20): 10–48550.
  32. Deep graph infomax. arXiv preprint arXiv:1809.10341.
  33. Attributed graph clustering: A deep attentional embedding approach. arXiv preprint arXiv:1906.06532.
  34. Mgae: Marginalized graph autoencoder for graph clustering. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 889–898.
  35. A fast hierarchical clustering algorithm for functional modules discovery in protein interaction networks. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 8(3): 607–620.
  36. Deep learning techniques for community detection in social networks. IEEE Access, 8: 96016–96026.
  37. Self-supervised graph convolutional network for multi-view clustering. IEEE Transactions on Multimedia, 24: 3182–3192.
  38. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826.
  39. Defining and evaluating network communities based on ground-truth. In Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics, 1–8.
  40. Modularity based community detection with deep learning. In IJCAI, volume 16, 2252–2258.
  41. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, 974–983.
  42. Hierarchical graph representation learning with differentiable pooling. Advances in neural information processing systems, 31.
  43. A survey of deep graph clustering: Taxonomy, challenge, and application. arXiv preprint arXiv:2211.12875.
  44. Link prediction based on graph neural networks. Advances in neural information processing systems, 31.
  45. BIRCH: an efficient data clustering method for very large databases. ACM sigmod record, 25(2): 103–114.
  46. Attributed graph clustering via adaptive graph convolution. arXiv preprint arXiv:1906.01210.
  47. Graph neural networks: A review of methods and applications. AI open, 1: 57–81.
Citations (5)
View on Semantic Scholar

Summary

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

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