Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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

Provable Filter for Real-world Graph Clustering (2403.03666v1)

Published 6 Mar 2024 in cs.LG

Abstract: Graph clustering, an important unsupervised problem, has been shown to be more resistant to advances in Graph Neural Networks (GNNs). In addition, almost all clustering methods focus on homophilic graphs and ignore heterophily. This significantly limits their applicability in practice, since real-world graphs exhibit a structural disparity and cannot simply be classified as homophily and heterophily. Thus, a principled way to handle practical graphs is urgently needed. To fill this gap, we provide a novel solution with theoretical support. Interestingly, we find that most homophilic and heterophilic edges can be correctly identified on the basis of neighbor information. Motivated by this finding, we construct two graphs that are highly homophilic and heterophilic, respectively. They are used to build low-pass and high-pass filters to capture holistic information. Important features are further enhanced by the squeeze-and-excitation block. We validate our approach through extensive experiments on both homophilic and heterophilic graphs. Empirical results demonstrate the superiority of our method compared to state-of-the-art clustering methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. C. Wang, S. Pan, G. Long, X. Zhu, and J. Jiang, “Mgae: Marginalized graph autoencoder for graph clustering,” in Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 2017., pp. 889–898.
  2. S. Fortunato and D. Hric, “Community detection in networks: A user guide,” Physics reports, vol. 659, pp. 1–44, 2016.
  3. X. Liu, “Incomplete multiple kernel alignment maximization for clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  4. X. Wang, P. Cui, J. Wang, J. Pei, W. Zhu, and S. Yang, “Community preserving network embedding,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
  5. W. Cui, H. Zhou, H. Qu, P. C. Wong, and X. Li, “Geometry-based edge clustering for graph visualization,” IEEE transactions on visualization and computer graphics, vol. 14, no. 6, pp. 1277–1284, 2008.
  6. F. Nie, J. Xue, W. Yu, and X. Li, “Fast clustering with anchor guidance,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  7. B. Perozzi and L. Akoglu, “Discovering communities and anomalies in attributed graphs: Interactive visual exploration and summarization,” ACM Transactions on Knowledge Discovery from Data (TKDD), vol. 12, no. 2, pp. 1–40, 2018.
  8. I. Cabreros, E. Abbe, and A. Tsirigos, “Detecting community structures in hi-c genomic data,” in 2016 Annual Conference on Information Science and Systems (CISS).   IEEE, 2016, pp. 584–589.
  9. A. Tsitsulin, J. Palowitch, B. Perozzi, and E. Müller, “Graph clustering with graph neural networks,” Journal of Machine Learning Research, vol. 24, no. 127, pp. 1–21, 2023.
  10. F. Tian, B. Gao, Q. Cui, E. Chen, and T.-Y. Liu, “Learning deep representations for graph clustering,” in Proceedings of the AAAI Conference on Artificial Intelligence, no. 1, 2014.
  11. S. Pan, R. Hu, S.-f. Fung, G. Long, J. Jiang, and C. Zhang, “Learning graph embedding with adversarial training methods,” IEEE transactions on cybernetics, vol. 50, no. 6, pp. 2475–2487, 2019.
  12. J. Cheng, Q. Wang, Z. Tao, D. Xie, and Q. Gao, “Multi-view attribute graph convolution networks for clustering,” in Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence, 2021, pp. 2973–2979.
  13. X. Yang, Y. Liu, S. Zhou, S. Wang, W. Tu, Q. Zheng, X. Liu, L. Fang, and E. Zhu, “Cluster-guided contrastive graph clustering network,” in Proc. of AAAI, 2023.
  14. Y. Liu, X. Yang, S. Zhou, X. Liu, S. Wang, K. Liang, W. Tu, and L. Li, “Simple contrastive graph clustering,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
  15. E. Pan and Z. Kang, “Multi-view contrastive graph clustering,” Advances in neural information processing systems, vol. 34, pp. 2148–2159, 2021.
  16. Z. Kang, Z. Liu, S. Pan, and L. Tian, “Fine-grained attributed graph clustering,” in Proceedings of the 2022 SIAM International Conference on Data Mining (SDM).   SIAM, 2022, pp. 370–378.
  17. J. Zhu, Y. Yan, L. Zhao, M. Heimann, L. Akoglu, and D. Koutra, “Beyond homophily in graph neural networks: Current limitations and effective designs,” Advances in Neural Information Processing Systems, vol. 33, pp. 7793–7804, 2020.
  18. ——, “Beyond homophily in graph neural networks: Current limitations and effective designs,” Advances in neural information processing systems, vol. 33, pp. 7793–7804, 2020.
  19. H. Mao, Z. Chen, W. Jin, H. Han, Y. Ma, T. Zhao, N. Shah, and J. Tang, “Demystifying structural disparity in graph neural networks: Can one size fit all?” Advances in neural information processing systems, 2023.
  20. Q. Li, Z. Han, and X.-M. Wu, “Deeper insights into graph convolutional networks for semi-supervised learning,” in Proceedings of the AAAI conference on artificial intelligence, vol. 32, no. 1, 2018.
  21. X. Li, R. Zhu, Y. Cheng, C. Shan, S. Luo, D. Li, and W. Qian, “Finding global homophily in graph neural networks when meeting heterophily,” in International Conference on Machine Learning.   PMLR, 2022.
  22. D. Cartwright and F. Harary, “Structural balance: a generalization of heider’s theory.” Psychological review, vol. 63, no. 5, p. 277, 1956.
  23. R. Lei, Z. Wang, Y. Li, B. Ding, and Z. Wei, “Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks,” Advances in Neural Information Processing Systems, 2022.
  24. M. Welling and T. N. Kipf, “Semi-supervised classification with graph convolutional networks,” in J. International Conference on Learning Representations, 2017.
  25. C. Wang, S. Pan, R. Hu, G. Long, J. Jiang, and C. Zhang, “Attributed graph clustering: A deep attentional embedding approach,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 3670–3676.
  26. T. Wang, J. Wu, Z. Zhang, W. Zhou, G. Chen, and S. Liu, “Multi-scale graph attention subspace clustering network,” Neurocomputing, vol. 459, pp. 302–314, 2021.
  27. H. Zhu and P. Koniusz, “Simple spectral graph convolution,” in 9th International Conference on Learning Representations, ICLR 2021, 2021.
  28. Z. Lin and Z. Kang, “Graph filter-based multi-view attributed graph clustering.” in IJCAI, 2021, pp. 2723–2729.
  29. Z. Lin, Z. Kang, L. Zhang, and L. Tian, “Multi-view attributed graph clustering,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 2, pp. 1872–1880, 2023.
  30. S. Abu-El-Haija, B. Perozzi, A. Kapoor, N. Alipourfard, K. Lerman, H. Harutyunyan, G. Ver Steeg, and A. Galstyan, “Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing,” in International Conference on Machine Learning.   PMLR, 2019, pp. 21–29.
  31. S. Luan, C. Hua, Q. Lu, J. Zhu, M. Zhao, S. Zhang, X.-W. Chang, and D. Precup, “Is heterophily a real nightmare for graph neural networks to do node classification?” arXiv preprint arXiv:2109.05641, 2021.
  32. D. Lim, F. Hohne, X. Li, S. L. Huang, V. Gupta, O. Bhalerao, and S. N. Lim, “Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods,” Advances in Neural Information Processing Systems, vol. 34, pp. 20 887–20 902, 2021.
  33. Z. Zhong, G. Gonzalez, D. Grattarola, and J. Pang, “Unsupervised network embedding beyond homophily,” IEEE Transactions on Machine Learning Research, 2022.
  34. X. Xie, W. Chen, Z. Kang, and C. Peng, “Contrastive graph clustering with adaptive filter,” Expert Systems with Applications, vol. 219, p. 119645, 2023.
  35. E. Pan and Z. Kang, “Beyond homophily: Reconstructing structure for graph-agnostic clustering,” in International conference on machine learning, 2023, pp. 1–10.
  36. J. Xu, E. Dai, D. Luo, X. Zhang, and S. Wang, “Learning graph filters for spectral gnns via newton interpolation,” arXiv preprint arXiv:2310.10064, 2023.
  37. J. Park, M. Lee, H. J. Chang, K. Lee, and J. Y. Choi, “Symmetric graph convolutional autoencoder for unsupervised graph representation learning,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6519–6528.
  38. Z. Hou, X. Liu, Y. Dong, C. Wang, J. Tang et al., “Graphmae: Self-supervised masked graph autoencoders,” SIGKDD, 2022.
  39. B. Chamberlain, J. Rowbottom, M. I. Gorinova, M. Bronstein, S. Webb, and E. Rossi, “Grand: Graph neural diffusion,” in International Conference on Machine Learning.   PMLR, 2021, pp. 1407–1418.
  40. Z. Yang, W. Cohen, and R. Salakhudinov, “Revisiting semi-supervised learning with graph embeddings,” in International Conference on Machine Learning.   PMLR, 2016, pp. 40–48.
  41. Y. Liu, W. Tu, S. Zhou, X. Liu, L. Song, X. Yang, and E. Zhu, “Deep graph clustering via dual correlation reduction,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 7, 2022, pp. 7603–7611.
  42. N. Mrabah, M. Bouguessa, M. F. Touati, and R. Ksantini, “Rethinking graph auto-encoder models for attributed graph clustering,” IEEE Transactions on Knowledge and Data Engineering, 2022.
  43. B. Rozemberczki, C. Allen, and R. Sarkar, “Multi-scale attributed node embedding,” Journal of Complex Networks, vol. 9, no. 2, p. cnab014, 2021.
  44. O. Platonov, D. Kuznedelev, M. Diskin, A. Babenko, and L. Prokhorenkova, “A critical look at the evaluation of gnns under heterophily: are we really making progress?” in The Eleventh International Conference on Learning Representations, 2023.
  45. H. Pei, B. Wei, K. C.-C. Chang, Y. Lei, and B. Yang, “Geom-gcn: Geometric graph convolutional networks,” in International Conference on Learning Representations, 2020.
  46. H. Zhu and P. Koniusz, “Simple spectral graph convolution,” in 9th International Conference on Learning Representations, ICLR 2021,, 2021.
  47. P. Zhu, J. Li, Y. Wang, B. Xiao, S. Zhao, and Q. Hu, “Collaborative decision-reinforced self-supervision for attributed graph clustering,” IEEE Transactions on Neural Networks and Learning Systems, 2022.
  48. P.-Y. Huang, R. Frederking et al., “Rwr-gae: Random walk regularization for graph auto encoders,” arXiv preprint arXiv:1908.04003, 2019.
  49. K. Hassani and A. H. Khasahmadi, “Contrastive multi-view representation learning on graphs,” in International Conference on Machine Learning.   PMLR, 2020, pp. 4116–4126.
  50. D. Bo, X. Wang, C. Shi, M. Zhu, E. Lu, and P. Cui, “Structural deep clustering network,” in Proceedings of The Web Conference 2020, 2020, pp. 1400–1410.
  51. W. Tu, S. Zhou, X. Liu, X. Guo, Z. Cai, E. Zhu, and J. Cheng, “Deep fusion clustering network,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 11, 2021, pp. 9978–9987.
  52. Y. Liu, W. Tu, S. Zhou, X. Liu, L. Song, X. Yang, and E. Zhu, “Deep graph clustering via dual correlation reduction,” in Proc. of AAAI, 2022.
  53. G. Cui, J. Zhou, C. Yang, and Z. Liu, “Adaptive graph encoder for attributed graph embedding,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 976–985.

Summary

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

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