Abstract
We introduce an approach to integrate bi-directional contexts in a generative tree model by means of structured transductions. We show how this can be efficiently realized as the composition of a top-down and a bottom-up generative model for trees, that are trained independently within a circular encoding-decoding scheme. The resulting input-driven generative model is shown to capture information concerning bi-directional contexts within its state-space. An experimental evaluation using the Jaccard generative kernel for trees is presented, indicating that the approach can achieve state of the art performance on tree classification benchmarks.
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
Diligenti, M., Frasconi, P., Gori, M.: Hidden tree markov models for document image classification. IEEE Trans. Pattern Anal. Mach. Intell. 25(4), 519–523 (2003)
Bacciu, D., Micheli, A., Sperduti, A.: Compositional generative mapping for tree-structured data - part I: Bottom-up probabilistic modeling of trees. IEEE Trans. Neural Netw. Learning Syst. 23(12), 1987–2002 (2012)
Bacciu, D., Micheli, A., Sperduti, A.: An input-output hidden Markov model for tree transductions. Neurocomputing 112, 34–46 (2013)
Micheli, A., Sona, D., Sperduti, A.: Contextual processing of structured data by recursive cascade correlation. IEEE Trans. on Neural Netw. 15(6), 1396–1410 (2004)
Hammer, B., Micheli, A., Sperduti, A.: Universal approximation capability of cascade correlation for structures. Neural Computation 17(5), 1109–1159 (2005)
Bacciu, D., Micheli, A., Sperduti, A.: Integrating bi-directional contexts in a generative kernel for trees. In: Proc. of the 2014 IEEE Int. Joint Conf. on Neural Netw., IJCNN 2014, pp. 4145–4151 (2014)
Durand, J., Goncalves, P., Guedon, Y., Rhone-Alpes, I., Montbonnot, F.: Computational methods for hidden Markov tree models-an application to wavelet trees. IEEE Trans. Signal Process. 52(9), 2551–2560 (2004)
Bacciu, D., Micheli, A., Sperduti, A.: A generative multiset kernel for structured data. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 57–64. Springer, Heidelberg (2012)
Denoyer, L., Gallinari, P.: Report on the XML mining track at INEX 2005 and INEX 2006: Categorization and clustering of XML documents. SIGIR Forum 41(1), 79–90 (2007)
Aiolli, F., Da San Martino, G., Sperduti, A.: Route kernels for trees. In: Proc. of ICML 2009, pp. 17–24. ACM (2009)
Gallicchio, C., Micheli, A.: Tree echo state networks. Neurocomputing 101, 319–337 (2013)
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
Bacciu, D., Micheli, A., Sperduti, A. (2014). Modeling Bi-directional Tree Contexts by Generative Transductions. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds) Neural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8834. Springer, Cham. https://doi.org/10.1007/978-3-319-12637-1_68
Download citation
DOI: https://doi.org/10.1007/978-3-319-12637-1_68
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12636-4
Online ISBN: 978-3-319-12637-1
eBook Packages: Computer ScienceComputer Science (R0)