A Bayesian classifier for learning from tensorial data

Liu, W, Chan, J, Leckie, C, Chen, F and Ramamohanarao, K 2013, 'A Bayesian classifier for learning from tensorial data', in H. Blockeel, K. Kersting, S. Nijssen, F. Zelezný (ed.) Proceedings of European Conference on Machine Learning and Pinciples and Practices of Knowledge Discovery in Databases (ECML PKDD) 2013, Prague, Czech Republic, 23-27 September 2013, pp. 483-498.


Document type: Conference Paper
Collection: Conference Papers

Title A Bayesian classifier for learning from tensorial data
Author(s) Liu, W
Chan, J
Leckie, C
Chen, F
Ramamohanarao, K
Year 2013
Conference name ECML PKDD: European Conference on Machine Learning and Pinciples and Practices of Knowledge Discovery in Databases
Conference location Prague, Czech Republic
Conference dates 23-27 September 2013
Proceedings title Proceedings of European Conference on Machine Learning and Pinciples and Practices of Knowledge Discovery in Databases (ECML PKDD) 2013
Editor(s) H. Blockeel, K. Kersting, S. Nijssen, F. Zelezný
Publisher Springer
Place of publication Germany
Start page 483
End page 498
Total pages 16
Abstract Traditional machine learning methods characterize data observations by feature vectors, where an entry of a vector denotes a scalar feature value of a data instance. While this data representation facilitates the application of conventional machine learning algorithms, in many cases it is not the best way of extracting all useful information from the data observations. In this paper we relax the (often unstated) assumption of vectorizing features of data instances, and allow a more natural representation of the data in a tensor format. Tensors are multi-mode (aka multi-way) arrays, of whom vectors (i.e., one-mode tensors) and matrices (i.e., two-mode tensors) are special cases. We show that the tensor representation captures useful information that is difficult to provide in the conventional vector format. More importantly, to effectively utilize the rich information contained in tensors, we propose a novel semi-naive Bayesian tensor classification method (which we call Bat) that builds predictive models directly on data in tensor form (instead of on their vectorizations). We apply Bat to supervised learning problems, and perform comprehensive experiments on classifying text documents and graphs, which demonstrate (1) the advantage of the tensor representation over conventional feature-vectorization approaches, and (2) the superiority of the proposed Bat tensor classifier over other existing learners.
Subjects Pattern Recognition and Data Mining
DOI - identifier 10.1007/978-3-642-40991-2
Copyright notice © Springer
ISBN 9783642409912
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 238 Abstract Views  -  Detailed Statistics
Created: Thu, 30 Apr 2015, 08:42:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us