Adaptive Graph Convolution Using Heat Kernel for Attributed Graph Clustering
Source abstract
Abstract
Attributed graphs contain a lot of node features and structural relationships, and how to utilize their inherent information sufficiently to improve graph clustering performance has attracted much attention. Although existing advanced methods exploit graph convolution to capture the global structure of an attributed graph and achieve obvious improvements for clustering results, they cannot determine the optimal neighborhood that reflects the relevant information of connected nodes in a graph. To address this limitation, we propose a novel adaptive graph convolution using a heat kernel model for attributed graph clustering (AGCHK), which exploits the similarity among nodes under heat diffusion to flexibly restrict the neighborhood of the center node and enforce the graph smoothness. Additionally, we take the Davies–Bouldin index (DBI) instead of the intra-cluster distance individually as the selection criterion to adaptively determine the order of graph convolution. The clustering results of AGCHK on three benchmark datasets—Cora, Citeseer, and Pubmed—are all more than 1% higher than the current advanced model AGC, and 12% on the Wiki dataset especially, which obtains a state-of-the-art result in the task of attributed graph clustering.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Complex Network Analysis Techniques · Advanced Graph Neural Networks · Advanced Clustering Algorithms Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
University of Chinese Academy of Sciences, Beijing 100049, China
Funding
Strategic Priority Research Program of Chinese Academy of Sciences
References (19)
Show source-provided references
1. Finding community structure in networks using the eigenvectors of matrices10.1103/PhysRevE.74.036104 ↗
2. Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24–27). Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623732 ↗
3. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-supervised classification with graph convolutional networks. Proceedings of the 5th International Conference on Learning Representations, Toulon, France.
4. Kipf, T.N., and Welling, M. (2016, January 10). Variational graph auto-encoders. Proceedings of the NIPS Workshop on Bayesian Deep Learning, Barcelona, Spain.
5. Wang, C., Pan, S., Long, G., Zhu, X., and Jiang, J. (2017, January 6–10). Mgae: Marginalized graph autoencoder for graph clustering. Proceedings of the 2017 ACM Conference on Information and Knowledge Management, Singapore.10.1145/3132847.3132967 ↗
6. Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., and Zhang, C. (2018, January 13–19). Adversarially regularized graph autoencoder for graph embedding. Proceedings of the Twenty-Seventh International Joint Conferences on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/362 ↗
7. Zhang, X., Liu, H., Li, Q., and Wu, X.-M. (2019, January 10–16). Attributed graph clustering via adaptive graph convolution. Proceedings of the International Joint Conferences on Artificial Intelligence, Macao, China.10.24963/ijcai.2019/601 ↗
8. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains10.1109/MSP.2012.2235192 ↗
9. Bruna, J., Zaremba, W., Szlam, A., and Lecun, Y. (2014, January 14–16). Spectral networks and locally connected networks on graphs. Proceedings of the 2nd International Conference on Learning Representations, Banff, AB, Canada.
10. Defferrard, M., Perraudin, N., and Vandergheynst, P. (2016, January 5–10). Convolutional neural networks on graphs with fast localized spectral filtering. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain.
11. Chung, F.R., and Graham, F.C. (1997). Spectral Graph Theory, American Mathematical Society.
12. Li, Q., Wu, X., Liu, H., Zhang, X., and Guan, Z. (2019, January 16–20). Label efficient semi-supervised learning via graph filtering. Proceedings of the Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00981 ↗
13. Xu, B., Shen, H., Cao, Q., Cen, K., and Cheng, X. (2019, January 10–16). Graph convolutional networks using heat kernel for semi-supervised learning. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, Macao, China.10.24963/ijcai.2019/267 ↗
14. Perraudin, N., Paratte, J., Shuman, D., Martin, L., Kalofolias, V., Vandergheynst, P., and Hammond, D.K. (2014). Gspbox: A toolbox for signal processing on graphs. arXiv.
15. Nikolentzos, G., Meladianos, P., and Vazirgiannis, M. (2017, January 4–9). Matching node embeddings for graph similarity. Proceedings of the Thirty-First Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10839 ↗
16. A Cluster Separation Measure10.1109/TPAMI.1979.4766909 ↗
17. Yang, C., Liu, Z., Zhao, D., Sun, M., and Chang, E.Y. (2015, January 25–31). Network representation learning with rich text information. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina.
18. Cao, S., Lu, W., and Xu, Q. (2016, January 12–17). Deep neural networks for learning graph representations. Proceedings of the Thirtieth Conference on Artificial Intelligence, Phoenix, AZ, USA.10.1609/aaai.v30i1.10179 ↗
19. Aggarwal, C.C., and Reddy, C.K. (2014). Data Clustering: Algorithms and Applications, CRC Press.10.1201/b15410 ↗