Abstract
Learning machines for pattern recognition, such as neural networks or support vector machines, are usually conceived to process real–valued vectors with predefined dimensionality even if, in many real–world applications, relevant information is inherently organized into entities and relationships between them. Instead, Graph Neural Networks (GNNs) can directly process structured data, guaranteeing universal approximation of many practically useful functions on graphs. GNNs, that do not strictly meet the definition of deep architectures, are based on the unfolding mechanism during learning, that, in practice, yields networks that have the same depth of the data structures they process. However, GNNs may be hindered by the long–term dependency problem, i.e. the difficulty in taking into account information coming from peripheral nodes within graphs — due to the local nature of the procedures for updating the state and the weights. To overcome this limitation, GNNs may be cascaded to form layered architectures, called Layered GNNs (LGNNs). Each GNN in the cascade is trained based on the original graph “enriched” with the information computed by the previous layer, to implement a sort of incremental learning framework, able to take into account progressively further information. The applicability of LGNNs will be illustrated both with respect to a classical problem in graph–theory and to pattern recognition problems in bioinformatics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
H. Bunke, K. Riesen, Recent advances in graph-based pattern recognition with applications in document analysis. Pattern Recognit. 44(5), 1057–1067 (2011)
M. Bianchini, F. Scarselli, Artificial neural networks for processing graphs with applications to image understanding: a survey, in Multimedia Techniques for Device and Ambient Intelligence, ed. by E. Damiani, J. Jeong (Springer, Berlin, 2009), pp. 179–199
C. Mooney, G. Pollastri, Beyond the twilight zone: automated prediction of structural properties of proteins by recursive neural networks and remote homology information. Proteins 77(1), 181–190 (2009)
A. Srinivasan, S. Muggleton, R.D. King, M.J.E. Sternberg, Mutagenesis: ILP experiments in a non–determinate biological domain, In Proceedings of the 4th International Workshop on Inductive Logic Programming, Gesellschaft für Mathematik und Datenverarbeitung MBH, pp. 217–232, 1994
J. Cheng, M.J. Sweredoski, P. Baldi, Accurate prediction of protein disordered regions by mining protein structure data. Data Min. Knowl. Discov. 11(3), 213–222 (2005)
M. Bianchini, M. Maggini, L. Sarti, Recursive neural networks and their applications to image processing, in Advances in Imaging and Electron Physics, vol. 140, ed. by P.W. Hawkes, (Elsevier – Academic Press, 2006), pp. 1–60
M. Bianchini, M. Maggini, L. Sarti, F. Scarselli, Recursive neural networks for processing graphs with labelled edges: theory and applications. Neural Netw. 18, 1040–1050 (2005)
V. Di Massa, G. Monfardini, L. Sarti, F. Scarselli, M. Maggini, M. Gori, A comparison between recursive neural networks and graph neural networks, in Proceedings of the IEEE International Joint Conference on Neural Networks, pp. 778–785, 2006
A.-C. Tsoi, M. Hagenbuchner, R. Chau, V. Lee, Unsupervised and supervised learning of graph domains, Studies in Computational Intelligence - Innovations in Neural Information Paradigms and Applications, vol. 247 (Springer, Berlin, 2009), pp. 43–65
P. Frasconi, M. Gori, A. Sperduti, A general framework for adaptive processing of data structures. IEEE Trans. Neural Netw. 9(5), 768–786 (1998)
F. Scarselli, M. Gori, A.-C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009)
W. Uwents, G. Monfardini, H. Blockeel, M. Gori, F. Scarselli, Neural networks for relational learning: an experimental comparison. Mach. Learn. 82(3), 315–349 (2011)
G. Monfardini, V. Di Massa, F. Scarselli, M. Gori, Graph neural networks for object localization, in Proceedings of ECAI 2006 (IOS Press, 2006), pp. 665–669
L. Di Noi, M. Hagenbuchner, F. Scarselli, A.-H. Tsoi, Web spam detection by probability mapping graph–SOMs and graph neural networks, in International Conference on Artificial Neural Networks (Springer, Berlin, 2010), pp. 372–381
D. Muratore, M. Hagenbuchner, F. Scarselli, A.-H. Tsoi, Sentence extraction by graph neural networks, in International Conference on Artificial Neural Networks (Springer, 2010), pp. 237–246
R. Chau, A.-H. Tsoi, M. Hagenbuchner, V. Lee, A conceptlink graph for text structure mining, in Proceedings of the Thirty–Second Australasian Conference on Computer Science, vol. 91, (Australian Computer Society, Inc., 2009), pp. 141–150
Y. Bengio, P. Simard, P. Frasconi, Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
M. Bianchini, F. Scarselli, On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25(8), 1553–1565 (2014)
G.E. Hinton, S. Osindero, Y. Teh, A fast learning algorithm for deep belief nets. Neural Comput. 2, 1527–1554 (2006)
M. Bianchini, M. Maggini, Supervised neural network models for processing graphs, in Handbook on Neural Information Processing (Springer, Berlin, 2013), pp. 67–96
M.A. Khamsi, An Introduction to Metric Spaces and Fixed Point Theory (Wiley, New York, 2001)
F.J. Pineda, Recurrent back-propagation and the dynamical approach to adaptive neural computation. Neural Comput. 1, 161–172 (1989)
N. Bandinelli, M. Bianchini, F. Scarselli, Learning long–term dependencies using layered graph neural networks, in The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, July 2010
D.R. Wood, An algorithm for finding a maximum clique in a graph. Oper. Res. Lett. 21(5), 211–217 (1997)
C. Hofbauer, H. Lohninger, A. Aszó, SURFCOMP: a novel graph-based approach to molecular surface comparison. J. Chem. Inf. Comput. Sci. 44(3), 837–847 (2004)
J. Konc, D. Janežič, A branch and bound algorithm for matching protein structures, in Adaptive and Natural Computing Algorithms, pp. 399–406, 2007
Q. Ouyang, P.D. Kaplan, S. Liu, A. Libchaber, DNA solution of the maximal clique problem. Science 278(5337), 446–449 (1997)
A. Broder, R. Kumar, F. Maghoul, P. Raghavan, S. Rajagopalan, R. Stata, A. Tomkins, J. Wiener, Graph structure in the web. Comput. Netw. 33(1), 309–320 (2000)
G. Palla, I. Derényi, I. Farkas, T. Vicsek, Uncovering the overlapping community structure of complex networks in nature and society. Nature 435, 814–818 (2005)
F. Scarselli, M. Gori, A.-C. Tsoi, M. Hagenbuchner, G. Monfardini, Computational capabilities of graph neural networks. IEEE Trans. Neural Netw. 20(1), 81–102 (2009)
B.A. Kunz, K. Ramachandran, E.J. Vonarx, DNA sequence analysis of spontaneous mutagenesis in saccharomyces cerevisiae. Genetics 148(4), 1491–1505 (1998)
G. Pollastri, A. Mclysaght, Porter: a new, accurate server for protein secondary structure prediction. Bioinformatics 21(8), 1719–1720 (2005)
M. Riedmiller, H. Braun, A direct algorithm method for faster backpropagation learning: the RPROP algorithm, in Proceedings of the International Conference on Neural Networks, vol. 1, (Portland (USA), 1993), pp. 586–591
W. Uwents, G. Monfardini, H. Blockeel, F. Scarselli, M Gori, Two connectionist models for graph processing: an experimental comparison on relational data, In European Conference on Machine Learning, pp. 211–220, 2006
M. Weisel, E. Proschak, G. Schneider, Pocket picker: analysis of ligand binding-sites with shape descriptors. Chem. Cent. J. 1, 1–7 (2007)
A.T.R. Laurie, R.M. Jackson, Q-SiteFinder: an energy-based method for the prediction of protein-ligand binding sites. Bioinformatics 21(9), 1908–1916 (2005)
B. Huang, M.M. Schroeder, LIGSITE csc: predicting ligand binding sites using the Connolly surface and degree of conservation. BMC Struct. Biol. 6(1), 19 (2006)
S. Butenko, W.E. Wilhelm, Clique-detection models in computational biochemistry and genomics. Eur. J. Oper. Res. 173(1), 1–17 (2006)
C. Yan, Y. Wang, A graph kernel method for DNA-binding site prediction. BMC Syst. Biol. 8(4), S10 (2014)
N. Kurumatani, H. Monji, T. Ohkawa, Binding site extraction by similar subgraphs mining from protein molecular surfaces, in IEEE 12th International Conference on Bioinformatics & Bioengineering (BIBE), 2012 (IEEE, New York, 2012), pp. 255–259
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Bianchini, M., Dimitri, G.M., Maggini, M., Scarselli, F. (2018). Deep Neural Networks for Structured Data. In: Pedrycz, W., Chen, SM. (eds) Computational Intelligence for Pattern Recognition. Studies in Computational Intelligence, vol 777. Springer, Cham. https://doi.org/10.1007/978-3-319-89629-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-89629-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-89628-1
Online ISBN: 978-3-319-89629-8
eBook Packages: EngineeringEngineering (R0)