Abstract
This paper presents the computational capabilities of Graph Neural Networks in application to 3D crystal structures. The Graph Neural Network model is described in detail in terms of encoding and unfolded network. Results of classifying selected 3D Bravais lattices are presented, confirming the ability of the Graph Neural Network Model to distinguish between structurally different lattices, lattices containing a single substitution and lattices containing a differently located substitution.
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
Preview
Unable to display preview. Download preview PDF.
References
Goulon-Sigwalt-Abram, A., Duprat, A., Dreyfus, G.: From hopfield nets to recursive networks to graph machines: numerical machine learning for structured data. Theoretical Computer Science 344(2), 298–334 (2005)
Pollack, J.B.: Recursive distributed representations. Artificial Intelligence 46(1), 77–105 (1990)
Sperduti, A.: Labelling recursive auto-associative memory. Connection Science 6(4), 429–459 (1994)
Goller, C., Kuchler, A.: Learning task-dependent distributed representations by backpropagation through structure. In: IEEE International Conference on Neural Networks, vol. 1, pp. 347–352. IEEE (1996)
Goulon, A., Duprat, A., Dreyfus, G.: Learning numbers from graphs. In: Applied Statistical Modelling and Data Analysis, Brest, France, pp. 17–20 (2005)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Transactions on Neural Networks 20(1), 61–80 (2009)
Goulon, A., Picot, T., Duprat, A., Dreyfus, G.: Predicting activities without computing descriptors: graph machines for QSAR. SAR and QSAR in Environmental Research 18(1-2), 141–153 (2007)
Goulon, A., Faraj, A., Pirngruber, G., Jacquin, M., Porcheron, F., Leflaive, P., Martin, P., Baron, G., Denayer, J.: Novel graph machine based QSAR approach for the prediction of the adsorption enthalpies of alkanes on zeolites. Catalysis Today 159(1), 74–83 (2011)
Saldana, D., Starck, L., Mougin, P., Rousseau, B., Creton, B.: On the rational formulation of alternative fuels: melting point and net heat of combustion predictions for fuel compounds using machine learning methods. SAR and QSAR in Environmental Research 24(4), 259–277 (2013)
Yong, S., Hagenbuchner, M., Tsoi, A., Scarselli, F., Gori, M.: XML document mining using graph neural network. Center for Computer Science, 354 (2006), http://inex.is.informatik.uni-duisburg.de/2006
Scarselli, F., Yong, S.L., Gori, M., Hagenbuchner, M., Tsoi, A.C., Maggini, M.: Graph neural networks for ranking web pages. In: Proceedings of the 2005 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 666–672. IEEE (2005)
Scarselli, F., Tsoi, A.C., Hagenbuchner, M., Noi, L.D.: Solving graph data issues using a layered architecture approach with applications to web spam detection. Neural Networks 48, 78–90 (2013)
Monfardini, G., Di Massa, V., Scarselli, F., Gori, M.: Graph neural networks for object localization. Frontiers in Artificial Intelligence and Applications 141, 665 (2006)
Quek, A., Wang, Z., Zhang, J., Feng, D.: Structural image classification with graph neural networks. In: International Conference on Digital Image Computing Techniques and Applications (DICTA), pp. 416–421. IEEE (2011)
Zhang, Y., Yang, S., Evans, J.R.G.: Revisiting Hume-Rotherys Rules with artificial neural networks. Acta Materialia 56(5), 1094–1105 (2008)
Willighagen, E., Wehrens, R., Melssen, W., De Gelder, R., Buydens, L.: Supervised self-organizing maps in crystal property and structure prediction. Crystal Growth & Design 7(9), 1738–1745 (2007)
Bianchini, M., Maggini, M., Sarti, L., Scarselli, F.: Recursive neural networks for processing graphs with labelled edges: Theory and applications. Neural Networks 18(8), 1040–1050 (2005)
Kittel, C., McEuen, P.: Introduction to solid state physics, vol. 8. Wiley, New York (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Barcz, A., Jankowski, S. (2014). Graph Neural Networks for 3D Bravais Lattices Classification. In: Golovko, V., Imada, A. (eds) Neural Networks and Artificial Intelligence. ICNNAI 2014. Communications in Computer and Information Science, vol 440. Springer, Cham. https://doi.org/10.1007/978-3-319-08201-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-08201-1_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08200-4
Online ISBN: 978-3-319-08201-1
eBook Packages: Computer ScienceComputer Science (R0)