Abstract
Deep Learning (DL) has been widely used in many applications, and its success is achieved with large training data. A key issue is how to provide a DL solution when there is no efficient training data to learn initially. In this paper, we explore a meta learning approach for a specific problem, subgraph isomorphism counting, which is a fundamental problem in graph analysis to count the number of a given pattern graph, p, in a data graph, g, that matches p. This problem is NP-hard, and needs large training data to learn by DL in nature. To solve this problem, we design a Gaussian Process (GP) model which combines graph neural network with Bayesian nonparametric, and we train the GP by a meta learning algorithm on a small set of training data. By meta learning, we obtain a generalized meta-model to better encode the information of data and pattern graphs and capture the prior of small tasks. We handle a collection of pairs (g, p), as a task, where some pairs may be associated with the ground-truth, and some pairs are the queries to answer. There are two cases. One is there are some with ground-truth (few-shot), and one is there is none with ground-truth (zero-shot). We provide our solutions for both. We conduct substantial experiments to confirm that our approach is robust to model degeneration on small training data, and our meta model can fast adapt to new queries by few/zero-shot learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. A. Cook. The complexity of theorem-proving procedures. In: Proceedings of the STOC, pp. 151–158 (1971)
Cordella, L.P., Foggia, P., Sansone, C., Vento, M.: A (sub)graph isomorphism algorithm for matching large graphs. IEEE Trans. Pattern Anal. Mach. Intell. 26(10), 1367–1372 (2004)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the NeurIPS 2017, pp. 1024–1034 (2017)
Liu, X., Pan, H., He, M., Song, Y., Jiang, X., Shang, L.: Neural subgraph isomorphism counting. In: Proceedings of the KDD 2020, pp. 1959–1969 (2020)
Park, Y., Ko, S., Bhowmick, S.S., Kim, K., Hong, K., Han, W.: G-CARE: a framework for performance benchmarking of cardinality estimation techniques for subgraph matching. In: Proceedings of the SIGMOD 2020, pp. 1099–1114 (2020)
Patacchiola, M., Turner, J., Crowley, E.J., Storkey, A.: Bayesian meta-learning for the few-shot setting via deep kernels. In: Proceedings of NeurIPS (2020)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press (2006)
Wilson, A.G., Adams, R.P.: Gaussian process kernels for pattern discovery and extrapolation. In: Proceedings of ICML, vol. 28, 1067–1075 (2013)
Wilson, A.G., Hu, Z., Salakhutdinov, R., Xing, E.P.: Deep kernel learning. In: Proceedings of AISTATS, vol. 51, pp. 370–378 (2016)
Yang, Q., Zhang, Y., Dai, W., Pan, S.J.: Transfer Learning. Cambridge University Press, Cambridge (2020)
Zhang, J., Dong, Y., Wang, Y., Tang, J., Ding, M.: Prone: fast and scalable network representation learning. In: Proceedings of the IJCAI 2019, pp. 4278–4284 (2019)
Zhao, K., Yu, J.X., He, Z., Li, R., Zhang, H.: Lightweight and accurate cardinality estimation by neural network gaussian process. In: SIGMOD 2022, pp. 973–987. ACM (2022)
Zhao, K., Yu, J.X., Zhang, H., Li, Q., Rong, Y.: A learned sketch for subgraph counting. In: Proceedings of SIGMOD 2021 (2021)
Acknowledgement
This work was supported by the Research Grants Council of Hong Kong, China, under No. 14203618, No. 14202919 and No. 14205520.
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
Zhao, K., Yu, J.X., He, Z., Rong, Y. (2023). Learning with Small Data: Subgraph Counting Queries. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13945. Springer, Cham. https://doi.org/10.1007/978-3-031-30675-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-30675-4_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30674-7
Online ISBN: 978-3-031-30675-4
eBook Packages: Computer ScienceComputer Science (R0)