Abstract
Recently, several techniques to learn the embedding for a given graph dataset have been proposed. Among them, Graph2vec is significant in that it unsupervisedly learns the embedding of entire graphs which is useful for graph classification. This paper develops an algorithm which improves Graph2vec. First, we point out two limitations of Graph2vec: (1) Edge labels cannot be handled and (2) Graph2vec does not always preserve structural information enough to evaluate the structural similarity, because it bundles the node label information and the structural information in extracting subgraphs. Our algorithm overcomes these limitations by exploiting the line graphs (edge-to-vertex dual graphs) of given graphs. Specifically, it complements either the edge label information or the structural information which Graph2vec misses with the embeddings of the line graphs. Our method is named as GL2vec (Graph and Line graph to vector) because it concatenates the embedding of an original graph to that of the corresponding line graph. Experimentally, GL2vec achieves significant improvements in graph classification task over Graph2vec for many benchmark datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural. Inf. Process. Syst. 26, 3111–3119 (2013)
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning, PMLR, vol. 32, no. 2, pp. 1188–1196 (2014)
Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: KDD 2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864 (2016)
Narayanan, A., Chandramohan, M., Venkatesan, R., Chen, L., Liu, Y., Jaiswal, S.: graph2vec: Learning Distributed Representations of Graphs. arXiv preprint arXiv:1707.05005. (2017)
Shervashidze, N., Schweitzer, P., van Leeuwen, E.J., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-Lehman graph kernels. J. Mach. Learn. Res. 12, 2539–2561 (2011)
Harary, F.: Graph Theory, pp. 71–83. Addison-Wesley, Boston (1972)
Zhu, X., Zhang, C., Pan, S., Yu, P.: Graph stream classification using labeled and unlabeled graphs. In: Proceedings of the 2013 IEEE 29th International Conference on Data Engineering, pp. 398–409 (2013)
Benchmark Data Sets for Graph Kernels. http://graphkernels.cs.tu-dortmund.de. Accessed 20 June 2019
Bai, L., Zhang, Z., Wang, C., Hancock, E.R.: An edge-based matching kernel for graphs through the directed line graphs. In: Proceedings of the International Conference on Computer Analysis of Images and Patterns, pp. 85–95 (2015)
Monti, F., Shchur, O., Bojchevski, A., Litany, O., Günnemann, S., Bronstein, M.M.: Dual-primal graph convolutional networks. arXiv preprint arXiv:1806.00770. (2018)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903. (2017)
Acknowledgments
This work was supported by JSPS KAKENHI Grant Number JP18K11311, 2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, H., Koga, H. (2019). GL2vec: Graph Embedding Enriched by Line Graphs with Edge Features. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11955. Springer, Cham. https://doi.org/10.1007/978-3-030-36718-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-36718-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36717-6
Online ISBN: 978-3-030-36718-3
eBook Packages: Computer ScienceComputer Science (R0)