Abstract
Graph neural networks (GNNs) have emerged as a powerful tool for analyzing graph data, where data are represented by nodes and edges. However, the conventional methods have limitations in analyzing graphs with diverse attributes and preserving crucial information during the graph embedding. As a result, there is a possibility of losing crucial information during the integration of individual nodes. To address this problem, we propose an attention-based readout with subgraphs for graph embedding that partitions the graph according to unique node attributes. This method ensures that important attributes are retained and prevents dilution of distinctive node features. The adjacency matrices and node feature matrices for the partitioned graphs go into a graph isomorphism network (GIN) to aggregate the features, where the attention mechanism merges the partitioned graphs to construct the whole graph embedding vector. Extensive experiments on six graph datasets demonstrate that the proposed method captures various local patterns and produces superior performance against the state-of-the-art methods for graph classification. Especially, on the challenging IMDB-MULTI dataset, our method achieves a significant performance gain of 27.87%p over the best method called MA-GCNN.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, B., Gong, N.Z., Fu, H.: GANG: Detecting fraudulent users in online social networks via guilt-by-association on directed graphs. In: International Conference on Data Mining (ICDM), pp. 465–474. IEEE (2017)
Bianchi, F.M., Grattarola, D., Livi, L., Alippi, C.: Graph neural networks with convolutional arma filters. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3496–3507 (2021)
Jin, N., Young, C., Wang, W.: GAIA: graph classification using evolutionary computation. In: ACM SIGMOD International Conference on Management of Data, pp. 879–890 (2010)
Kim, J.-Y., Cho, S.-B.: A systematic analysis and guidelines of graph neural networks for practical applications. Expert Syst. Appl. 184, 115466 (2021)
Park, K.-W., Cho, S.-B.: A residual graph convolutional network with spatio-temporal features for autism classification from fMRI brain images. Appl. Soft Comput. 142, 110363 (2023)
Peng, H., Li, J., Gong, Q., Ning, Y., Wang, S., He, Li.: Motif-matching based subgraph-level attentional convolutional network for graph classification. Proc. AAAI Conf. Artif. Intell. 34(04), 5387–5394 (2020)
Yang, J., Peilin Zhao, Y., Rong, C.Y., Li, C., Ma, H., Huang, J.: Hierarchical graph capsule network. Proc. AAAI Conf. Artif. Intell. 35(12), 10603–10611 (2021). https://doi.org/10.1609/aaai.v35i12.17268
Park, K.-W., Bu, S.-J., Cho, S.-B.: Learning dynamic connectivity with residual-attention network for autism classification in 4D fMRI brain images. In: Yin, H., et al. (eds.) IDEAL 2021. LNCS, vol. 13113, pp. 387–396. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-91608-4_38
Park, K.W., Cho, S.B.: A vision transformer enhanced with patch encoding for malware classification. In: Yin, H., Camacho, D., Tino, P. (eds.) Intelligent Data Engineering and Automated Learning – IDEAL 2022. IDEAL 2022. Lecture Notes in Computer Science, vol. 13756. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-21753-1_29
Kim, K.-J., Cho, S.-B.: Personalized mining of web documents using link structures and fuzzy concept networks. Appl. Soft Comput. 7, 398–410 (2007)
Wang, H., Zhang, F., Zhao, M., Li, W., Xie, X., Guo, M.: Multi-task feature learning for knowledge graph enhanced recommendation. In: World Wide Web Conference, pp. 2000–2010 (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 22, pp. 1225–1234 (2016)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Yang, Y., Feng, Z., Song, M., Wang, X.: Factorizable graph convolutional networks. Adv. Neural. Inf. Process. Syst. 33, 20286–20296 (2020)
Cotta, L., Morris, C., Ribeiro, B.: Reconstruction for powerful graph representations. Adv. Neural. Inf. Process. Syst. 34, 1713–1726 (2021)
Papp, P.A., Martinkus, K., Faber, L., Wattenhofer, R.: DropGNN: random dropouts increase the expressiveness of graph neural networks. Adv. Neural. Inf. Process. Syst. 34, 21997–22009 (2021)
Satuluri, V., Parthasarathy, S.: Symmetrizations for clustering directed graphs. Int. Conf. Extending Database Technol. 14, 343–354 (2011)
Müller, E.: Graph clustering with graph neural networks. J. Mach. Learn. Res. 24, 1–21 (2023)
Schaeffer, S.E.: Graph clustering. Comput. Sci. Rev. 1, 27–64 (2007)
Azari, M., Iranmanesh, A.: Computing the eccentric-distance sum for graph operations. Discret. Appl. Math. 161, 2827–2840 (2013)
Borgatti, S.P., Everett, M.G.: A graph-theoretic perspective on centrality. Soc. Netw. 28, 466–484 (2006)
Zhang, J., Luo, Y.: Degree centrality, betweenness centrality, and closeness centrality in social network. In: International Conference on Modelling, Simulation and Applied Mathematics, vol. 2, pp. 300–303. Atlantis Press (2017)
Cho, S.-B., Shimohara, K.: Evolutionary learning of modular neural networks with genetic programming. Appl. Intell. 9, 191–200 (1998)
Yanardag, P., Vishwanathan, S.: Deep graph kernels. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 22, pp. 1365–1374 (2015)
Rozemberczki, B., Kiss, O., Sarkar, R.: An api oriented open-source python framework for unsupervised learning on graphs. arXiv preprint arXiv:2003.04819 10 (2020)
Oettershagen, L., Kriege, N.M., Morris, C., Mutzel, P.: Temporal graph kernels for classifying dissemination processes. In: International Conference on Data Mining, pp. 496–504. SIAM (2020)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural. Inf. Process. Syst. 30, 1025–1035 (2017)
Acknowledgements
This work was supported by IITP grant funded by the Korean government (MSIT) (No. 2020-0-01361, Artificial Intelligence Graduate School Program (Yonsei University)), an ETRI grant funded by the Korean government (23ZS1100, Core Technology Research for Self-Improving Integrated Artificial Intelligence System), and the Yonsei Fellow Program funded by Lee Youn Jae.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Moon, HJ., Cho, SB. (2023). A Subgraph Embedded GIN with Attention for Graph Classification. In: Quaresma, P., Camacho, D., Yin, H., Gonçalves, T., Julian, V., Tallón-Ballesteros, A.J. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404. Springer, Cham. https://doi.org/10.1007/978-3-031-48232-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-48232-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48231-1
Online ISBN: 978-3-031-48232-8
eBook Packages: Computer ScienceComputer Science (R0)