Abstract
This paper introduces ReGenGraph, a new method for graph regression that combines two well-known modules: an autoencoder and a graph autoencoder. The main objective of our proposal is to split the knowledge in the graph nodes into semantic and structural knowledge during the embedding process. It uses the autoencoder to extract the semantic knowledge and the graph autoencoder to extract the structural knowledge. The resulting embedded vectors of both modules are then combined and used for graph regression to predict a global property of the graph. The method demonstrates improved performance compared to classical methods, i.e., autoencoders or graph autoencoders alone. The approach has been applied to predict the binding energy of chemical compounds represented as attributed graphs but could be used in other fields as well.
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
Similar content being viewed by others
References
Fadlallah, S., Julià, C., Serratosa, F.: Graph regression based on graph autoencoders. In: Krzyzak, A., Suen, C.Y., Torsello, A., Nobile, N. (eds.) Structural, Syntactic, and Statistical Pattern Recognition, pp. 142–151. Springer International Publishing, Cham (2022)
Garcia-Hernandez, C., Fernández, A., Serratosa, F.: Ligand-based virtual screening using graph edit distance as molecular similarity measure. J. Chem. Inf. Model. 59(4), 1410–1421 (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Kingma, D.P., Rezende, D.J., Mohamed, S., Welling, M.: Semi-supervised learning with deep generative models (2014)
Kipf, T.N.: Deep Learning with Graph-Structured Representations. Ph.D. thesis, University of Amsterdam (2020)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. CoRR abs/1609.02907 (2016). arXiv:1609.02907
Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. AIChE J. 37, 233–243 (1991)
Le, T., Le, N., Le, B.: Knowledge graph embedding by relational rotation and complex convolution for link prediction. Expert Syst. Appl. 214, 119122 (2023). https://doi.org/10.1016/j.eswa.2022.119122
Majumdar, A.: Graph structured autoencoder. Neural Netw. 106, 271–280 (2018). https://doi.org/10.1016/j.neunet.2018.07.016
Naveed, M., et al.: A reverse vaccinology approach to design an mrna-based vaccine to provoke a robust immune response against hiv-1. Acta Biochimica Polonica 70(2) (2023). https://doi.org/10.18388/abp.2020_6696
Remesh, S., et al.:Unconventional peptide presentation by major histocompatibility complex (mhc) class i allele hla-a*02:01:breaking confinement. J. Biol. Chem. 292(13) (2017). https://doi.org/10.1074/jbc.M117.776542
Reynisson, B., Alvarez, B., Paul, S., Peters, B., Nielsen, M.: Netmhcpan-4.1 and netmhciipan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data. Nucleic Acids Res. 48(W1), W449–W454 (2020). https://doi.org/10.1093/nar/gkaa379
Rica, E., Álvarez, S., Serratosa, F.: Ligand-based virtual screening based on the graph edit distance. Int. J. Mol. Sci. 22(23), 12751 (2021)
Schymkowitz, J., Borg, J., Stricher, F., Nys, R., Rousseau, F., Serrano, L.: The foldx web server: an online force field. Nucleic acids research 33(Web Server issue) (2005). https://doi.org/10.1093/nar/gki387
Serratosa, Francesc: Redefining the graph edit distance. SN Comput. Sci. 2(6), 1–7 (2021). https://doi.org/10.1007/s42979-021-00792-5
Serratosa, F., Cortés, X.: Graph edit distance: moving from global to local structure to solve the graph-matching problem. Pattern Recogn. Lett. 65, 204–210 (2015)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Vita, R., et al.: The immune epitope database (iedb): 2018 update. Nucleic Acids Res. 47(D1) (2018). https://doi.org/10.1093/nar/gky1006
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Yu, P.S.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2021). https://doi.org/10.1109/TNNLS.2020.2978386
Acknowledgements
This research is supported by the Universitat Rovira i Virgili through the Martí Franquès grant and partially funded by AGAUR research group 2021SGR-00111: “ASCLEPIUS: Smart Technology for Smart Healthcare”.
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
Fadlallah, S., Segura Alabart, N., Julià, C., Serratosa, F. (2023). Splitting Structural and Semantic Knowledge in Graph Autoencoders for Graph Regression. In: Vento, M., Foggia, P., Conte, D., Carletti, V. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2023. Lecture Notes in Computer Science, vol 14121. Springer, Cham. https://doi.org/10.1007/978-3-031-42795-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-42795-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42794-7
Online ISBN: 978-3-031-42795-4
eBook Packages: Computer ScienceComputer Science (R0)