Abstract
Both data access and data collection have become increasingly easy over the past decade, leading to rapid developments in many areas of intelligent information processing. In some cases, however, the amount of data is still not sufficiently large (e.g. in some machine learning applications). Data augmentation is a widely used mechanism to increase the available data in such cases. Current augmentation methods are mostly developed for statistical data and only a small part of these methods is directly applicable to graphs. In a recent research project, a novel encoding of pairwise graph matchings is introduced. The basic idea of this encoding, termed matching-graph, is to formalize the stable cores of pairs of patterns by means of graphs. In the present paper, we propose to use these matching-graphs to augment training sets of graphs in order to stabilize the training process of state-of-the-art graph neural networks. In an experimental evaluation on five graph data sets, we show that this novel augmentation technique is able to significantly improve the classification accuracy of three different neural network models.
Supported by Swiss National Science Foundation (SNSF) Project Nr. 200021\(\_\)188496.
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
Notes
- 1.
- 2.
The edge edit operations are implicitly given by the node edit operations and are thus not considered in \(\lambda (g,g')\).
- 3.
- 4.
The statistical significance is computed via Z-test using a significance level of \(\alpha = 0.05\).
References
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6, 60 (2019). https://doi.org/10.1186/s40537-019-0197-0
Chinbat, V., Bae, S.H.: Ga3n: generative adversarial au-toaugment network. Pattern Recogn. 127, 108637 (2022). https://doi.org/10.1016/j.patcog.2022.108637, https://www.sciencedirect.com/science/article/pii/S0031320322001182
Sahin, G.G., Steedman, M.: Data augmentation via dependency tree morphing for low-resource languages. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October - 4 November 2018, pp. 5004–5009. Association for Computational Linguistics (2018). https://doi.org/10.18653/v1/d18-1545
Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. Pattern Recognit Artif Intell. 18(3), 265–298 (2004). https://doi.org/10.1142/S0218001404003228
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009). https://doi.org/10.1109/TNN.2008.2005605
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019). https://openreview.net/forum?id=ryGs6iA5Km
Morris, C., et al.: Weisfeiler and leman go neural: higher-order graph neural networks. In: The 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, The 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, 27 January - 1 February 2019, pp. 4602–4609. AAAI Press (2019). https://doi.org/10.1609/aaai.v33i01.33014602
Zhao, T., Liu, Y., Neves, L., Woodford, O.J., Jiang, M., Shah, N.: Data augmentation for graph neural networks. In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2–9 February 2021, pp. 11015–11023. AAAI Press (2021). https://ojs.aaai.org/index.php/AAAI/article/view/17315
Zhou, J., Shen, J., Yu, S., Chen, G., Xuan, Q.: M-evolve: structural-mapping-based data augmentation for graph classification. IEEE Trans. Netw. Sci. Eng. 8(1), 190–200 (2021). https://doi.org/10.1109/TNSE.2020.3032950
Park, J., Shim, H., Yang, E.: Graph transplant: node saliency-guided graph mixup with local structure preservation. In: 36th AAAI Conference on Artificial Intelligence, AAAI 2022, 34th Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The 12th Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, 22 February - 1 March 2022, pp. 7966–7974. AAAI Press (2022). https://ojs.aaai.org/index.php/AAAI/article/view/20767
Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April - 3 May 2018, Conference Track Proceedings. OpenReview.net (2018), https://openreview.net/forum?id=r1Ddp1-Rb
Kipf, T.N., Welling, M.: Variational graph auto-encoders. CoRR abs/1611.07308 (2016). arxiv.org/abs/1611.07308
Simonovsky, M., Komodakis, N.: GraphVAE: towards generation of small graphs using variational autoencoders. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 412–422. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_41
Wang, H., et al.: Graphgan: graph representation learning with generative adversarial nets. In: McIlraith, S.A., Weinberger, K.Q. (eds.) Proceedings of the 32st AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2–7 February 2018, pp. 2508–2515. AAAI Press (2018). www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16611
Cao, N.D., Kipf, T.: Molgan: An implicit generative model for small molecular graphs. CoRR abs/1805.11973 (2018). arxiv.org/abs/1805.11973
Bunke, H., Allermann, G.: Inexact graph matching for structural pattern recognition. Pattern Recognit. Lett. 1(4), 245–253 (1983). https://doi.org/10.1016/0167-8655(83)90033-8
Fuchs, M., Riesen, K.: Matching of matching-graphs - a novel approach for graph classification. In: 25th International Conference on Pattern Recognition, ICPR 2020, Virtual Event/Milan, Italy, 10–15 January 2021, pp. 6570–6576. IEEE (2020). https://doi.org/10.1109/ICPR48806.2021.9411926
Chen, X., Huo, H., Huan, J., Vitter, J.S.: Fast computation of graph edit distance. CoRR abs/1709.10305 (2017). arxiv.org/abs/1709.10305
Fischer, A., Suen, C.Y., Frinken, V., Riesen, K., Bunke, H.: Approximation of graph edit distance based on hausdorff matching. Pattern Recognit. 48(2), 331–343 (2015). https://doi.org/10.1016/j.patcog.2014.07.015
Riesen, K., Bunke, H.: Approximate graph edit distance computation by means of bipartite graph matching. Image Vis. Comput. 27(7), 950–959 (2009). https://doi.org/10.1016/j.imavis.2008.04.004
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)
Ying, Z., You, J., Morris, C., Ren, X., Hamilton, W., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Guyon, I., (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4–9 December 2017, Long Beach, CA, USA, pp. 1024–1034 (2017). https://proceedings.neurips.cc/paper/2017/hash/5dd9db5e033da9c6fb5ba83c7a7ebea9-Abstract.html
Errica, F., Podda, M., Bacciu, D., Micheli, A.: A fair comparison of graph neural networks for graph classification. In: Proceedings of the 8th International Conference on Learning Representations (ICLR) (2020)
Morris, C., Kriege, N.M., Bause, F., Kersting, K., Mutzel, P., Neumann, M.: Tudataset: a collection of benchmark datasets for learning with graphs. In: ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+ 2020) (2020). www.graphlearning.io
Kriege, N.M., Fey, M., Fisseler, D., Mutzel, P., Weichert, F.: Recognizing cuneiform signs using graph based methods. In: International Workshop on Cost-Sensitive Learning, COST@SDM 2018, San Diego, California, USA, 5 May 2018. Proceedings of Machine Learning Research, vol. 88, pp. 31–44. PMLR (2018). http://proceedings.mlr.press/v88/kriege18a.html
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
Fuchs, M., Riesen, K. (2023). Graph Augmentation for Neural Networks Using Matching-Graphs. In: El Gayar, N., Trentin, E., Ravanelli, M., Abbas, H. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2022. Lecture Notes in Computer Science(), vol 13739. Springer, Cham. https://doi.org/10.1007/978-3-031-20650-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-20650-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20649-8
Online ISBN: 978-3-031-20650-4
eBook Packages: Computer ScienceComputer Science (R0)