Abstract
Graph convolutional network (GCN) has been widely used in handling various graph data analysis tasks. For graph classification tasks, existing work on graph classification mainly focuses on two aspects of graph similarity: physical structure and practical property. In this paper, we consider the problem of graph classification from a new perspective, namely structural properties. Graph similarity is defined based on structural properties such as maximum clique, minimum vertex coverage, and minimum dominating set of graphs. To capture these structural features, we design an adaptive motif to mine the higher-order connectivity information among nodes. Furthermore, to obtain the unique down-sampling in graph pooling stage, we propose a de-correlation pooling approach. Our extensive experiments on several artificially generated datasets show that our proposed model can effectively classify graphs with similar structural property. It is also experimentally compared with the baseline approach to demonstrate the effectiveness of our adaptive motif GCNs.
Similar content being viewed by others
References
Luo F, Guo W, Yu Y, Chen G (2017) A multi-label classification algorithm based on kernel extreme learning machine. Neurocomputing 260:313–320
Shervashidze N, Schweitzer P, Van J, Mehlhorn K, Borgwardt K (2011) Weisfeiler–Lehman graph kernels. J Mach Learn Res 12(9):2539–2561
Shervashidze N, Vishwanathan SVN, Petri T, Mehlhorn K, Borgwardt K (2009) Efficient graphlet kernels for large graph comparison. In: Artificial Intelligence and Statistics, pp 488–495
Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742–754
Nikolentzos G, Meladianos P, Vazirgiannis M (2017) Matching node embeddings for graph similarity. In: Thirty-First AAAI Conference on Artificial Intelligence
Chen F, Deng P, Wan J, Zhang D, Vasilakos V, Rong X (2015) Data mining for the internet of things: literature review and challenges. Int J Distrib Sens Netw 11(8):431047
Bai Y, Ding H, Bian S, Chen T, Sun Y, Wang W (2018) Graph edit distance computation via graph neural networks. arXiv:1808.05689
Nguyen H, Maeda I, Oono K (2017) Semi-supervised learning of hierarchical representations of molecules using neural message passing. arXiv:1711.10168
Levie R, Monti F, Bresson X, Bronstein M (2018) Cayleynets: graph convolutional neural networks with complex rational spectral filters. IEEE Trans Signal Process 67(1):97–109
Fout A, Byrd J, Shariat B, Ben-Hur A (2017) Protein interface prediction using graph convolutional networks. Adv Neural Inf Process Syst 30:6530–6539
Ryu S, Lim J, Hong H, Kim Y (2018) Deeply learning molecular structure-property relationships using attention-and gate-augmented graph convolutional network. arXiv:1805.10988
Shang C, Liu Q, Chen S, Sun J, Lu J, Yi J, Bi J (2018) Edge attention-based multi-relational graph convolutional networks
Kim C, Moon H, Hwang J (2019) NEAR: neighborhood edge AggregatoR for graph classification. arXiv:1909.02746
Wang X, Zhu M, Bo D, Cui P, Shi C, Pei J (2020) AM-GCN: adaptive multi-channel graph convolutional networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1243–1253
Khalil E, Dai H, Zhang Y, Dilkina B, Song L (2017) Learning combinatorial optimization algorithms over graphs. Adv Neural Inf Process Syst 30:6348–6358
Hastad J (1996) Clique is hard to approximate within \(n^{1-\epsilon }\). In: Proceedings of 37th Conference on Foundations of Computer Science. IEEE, pp 627–636
Grandoni F (2006) A note on the complexity of minimum dominating set. J Discrete Algorithms 4(2):209–214
Luce D, Perry D (1949) A method of matrix analysis of group structure. Psychometrika 14(2):95–116
Allan B, Laskar R (1978) On domination and independent domination numbers of a graph. Discrete Math 23(2):73–76
Gross L, Yellen J (2005) Graph theory and its applications. CRC Press, Boca Raton
Li Y, Gu C, Dullien T, Vinyals O, Kohli P (2019) Graph matching networks for learning the similarity of graph structured objects. arXiv:1904.12787
Benson R, Gleich F, Leskovec J (2016) Higher-order organization of complex networks. Science 353(6295):163–166
Ugander J, Backstrom L, Kleinberg J (2013) Subgraph frequencies: mapping the empirical and extremal geography of large graph collections. In: Proceedings of the 22nd International Conference on World Wide Web, pp 1307–1318
Rotabi R, Kamath K, Kleinberg J, Sharma A (2017) Detecting strong ties using network motifs. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp 983–992
Prulj N (2007) Biological network comparison using graphlet degree distribution. Bioinformatics 23(2):e177–e183
Sporns O, Ktter R (2004) Motifs in brain networks. PLoS Biol 2(11):e369
Paranjape A, Benson R, Leskovec J (2017) Motifs in temporal networks. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp 601–610
Li Z, Huang L, Wang D, Lai H (2019) EdMot: an edge enhancement approach for motif-aware community detection. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 479–487
Li X, Cao C, Zhang T (2020) Block diagonal dominance-based dynamic programming for detecting community. J Supercomput 76:8627–8640
Zhao H, Xu X, Song Y, Lee L, Chen Z, Gao H (2018) Ranking users in social networks with higher-order structures. In: AAAI, pp 232–240
Zhao H, Zhou Y, Song Y, Lee D (2019) Motif enhanced recommendation over heterogeneous information network. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp 2189–2192
Xu K, Hu W, Leskovec J, Jegelka S (2018) How powerful are graph neural networks?
Ying Z, You J, Morris C, Ren X, Hamilton W, Leskovec J (2018) Hierarchical graph representation learning with differentiable pooling. In: Advances in Neural Information Processing Systems, pp 4800–4810
Gao H, Ji S (2019) Graph u-nets. arXiv:1905.05178
Lee J, Lee I, Kang J (2019) Self-attention graph pooling. arXiv:1904.08082
Diehl F (2019) Edge contraction pooling for graph neural networks. CoRR
Ma Y, Wang S, Aggarwal C, Tang J (2019) Graph convolutional networks with eigenpooling. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 723–731
Gao X, Xiong H, Frossard P (2019) iPool-information-based pooling in hierarchical graph neural networks. arXiv:1907.00832
Kipf T, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907
Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579–2605
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grants No. 61907024, the Natural Science Foundation of Fujian Province under Grants No. 2020J05161, and the Starting Research Fund from Minnan Normal University (Project No. KJ18009).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, X., Wu, H. Toward graph classification on structure property using adaptive motif based on graph convolutional network. J Supercomput 77, 8767–8786 (2021). https://doi.org/10.1007/s11227-021-03628-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-03628-4