Abstract
Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. In this work, we systematically study the impact of community structure on the performance of GNNs in semi-supervised node classification on graphs. Following an ablation study on six datasets, we measure the performance of GNNs on the original graphs, and the change in performance in the presence and the absence of community structure. Our results suggest that communities typically have a major impact on the learning process and classification performance. For example, in cases where the majority of nodes from one community share a single classification label, breaking up community structure results in a significant performance drop. On the other hand, for cases where labels show low correlation with communities, we find that the graph structure is rather irrelevant to the learning process, and a feature-only baseline becomes hard to beat. With our work, we provide deeper insights in the abilities and limitations of GNNs, including a set of general guidelines for model selection based on the graph structure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The implementation and technical details can be found on https://github.com/sqrhussain/structure-in-gnn.
References
Barabási, A.L.: Network science. Philos. Trans. Royal Soc. A: Math. Phys. Eng. Sci. 371(1987), 20120375 (2013)
Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theory Exp. 2008(10), P10008 (2008)
Bojchevski, A., Günnemann, S.: Deep Gaussian embedding of graphs: unsupervised inductive learning via ranking. In: International Conference on Learning Representations, pp. 1–13 (2018)
Chapelle, O., Scholkopf, B., Zien, A.: Semi-supervised learning. IEEE Trans. Neural Netw. 20(3), 542–542 (2009). (chapelle, o. et al., eds.; 2006)[book reviews]
Cherifi, H., Palla, G., Szymanski, B.K., Lu, X.: On community structure in complex networks: challenges and opportunities. Appl. Netw. Sci. 4(1), 1–35 (2019)
Craven, M., DiPasquo, D., Freitag, D., McCallum, A., Mitchell, T., Nigam, K., Slattery, S.: Learning to extract symbolic knowledge from the World Wide Web. In: Proceedings of the National Conference on Artificial Intelligence, pp. 509–516 (1998)
Erdős, P., Rényi, A.: On the evolution of random graphs. Publ. Math. Inst. Hung. Acad. Sci 5(1), 17–60 (1960)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp. 1024–1034 (2017)
Hasani-Mavriqi, I., Kowald, D., Helic, D., Lex, E.: Consensus dynamics in online collaboration systems. Comput. Soc. Netw. 5(1), 2 (2018)
Holland, P.W., Laskey, K.B., Leinhardt, S.: Stochastic blockmodels: first steps. Soc. Netw. 5(2), 109–137 (1983)
Karrer, B., Newman, M.E.: Stochastic blockmodels and community structure in networks. Phys. Rev. E 83(1), 016107 (2011)
Kim, J., Wilhelm, T.: What is a complex graph? Phys. A: Stat. Mech. Appl. 387(11), 2637–2652 (2008)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: Graph neural networks meet personalized PageRank. In: 7th International Conference on Learning Representations, ICLR 2019 (2019)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (2018)
Loukas, A.: What graph neural networks cannot learn: depth vs width. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=B1l2bp4YwS
Namata, G., London, B., Getoor, L., Huang, B., EDU, U.: Query-driven active surveying for collective classification. In: 10th International Workshop on Mining and Learning with Graphs, Vol. 8 (2012)
Newman, M.E.: The structure and function of complex networks. SIAM Rev. 45(2), 167–256 (2003)
Press, W.H., Teukolsky, S.A., Flannery, B.P., Vetterling, W.T.: Numerical Recipes in FORTRAN 77. FORTRAN numerical recipes: the art of scientific computing, vol. 1. Cambridge University Press, Cambridge (1992)
Ribeiro, M.H., Calais, P.H., Santos, Y.A., Almeida, V.A., Meira, Jr., W.: “like sheep among wolves”: Characterizing hateful users on twitter (2017). arXiv preprint: arXiv:1801.00317
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93–93 (2008)
Shchur, O., Mumme, M., Bojchevski, A., Günnemann, S.: Pitfalls of graph neural network evaluation. In: Relational Representation Learning Workshop, NeurIPS 2018 (2018)
Tiao, L., Elinas, P., Nguyen, H., Bonilla, E.V.: Variational Spectral Graph Convolutional Networks. In: Graph Representation Learning Workshop, NeurIPS 2019 (2019)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph Attention Networks. International Conference on Learning Representations (2018). https://openreview.net/forum?id=rJXMpikCZ. (Accepted as poster)
Wu, F., Zhang, T., Souza Jr., A.H.., Fifty, C., Yu, T., Weinberger, K.Q.: Simplifying graph convolutional networks (2019). arXiv preprint: arXiv:1902.07153
Xu, K., Jegelka, S., Hu, W., Leskovec, J.: How powerful are graph neural networks? In: 7th International Conference on Learning Representations, ICLR 2019 (2019)
Zhu, X., Ghahramani, Z., Lafferty, J.D.: Semi-supervised learning using Gaussian fields and harmonic functions. In: Proceedings of the 20th International conference on Machine learning (ICML2003), pp. 912–919 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hussain, H., Duricic, T., Lex, E., Kern, R., Helic, D. (2021). On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks. In: Benito, R.M., Cherifi, C., Cherifi, H., Moro, E., Rocha, L.M., Sales-Pardo, M. (eds) Complex Networks & Their Applications IX. COMPLEX NETWORKS 2020 2020. Studies in Computational Intelligence, vol 944. Springer, Cham. https://doi.org/10.1007/978-3-030-65351-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-65351-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65350-7
Online ISBN: 978-3-030-65351-4
eBook Packages: EngineeringEngineering (R0)