Abstract
This paper studies parallel training of an improved neural network for text categorization. With the explosive growth on the amount of digital information available on the Internet, text categorization problem has become more and more important, especially when millions of mobile devices are now connecting to the Internet. Improved back-propagation neural network (IBPNN) is an efficient approach for classification problems which overcomes the limitations of traditional BPNN. In this paper, we utilize parallel computing to speedup the neural network training process of IBPNN. The parallel IBNPP algorithm for text categorization is implemented on a Sun Cluster with 34 nodes (processors). The communication time and speedup for the parallel IBPNN versus various number of nodes are studied. Experiments are conducted on various data sets and the results show that the parallel IBPNN together with SVD technique achieves fast computational speed and high text categorization correctness.
Similar content being viewed by others
References
ai.mit. 20-news-18828 version: http://www.ai.mit.edu/jrennie/20Newsgroups (2010)
Chen, G.A., Yu, X.H., Cheng, S.X.: Acceleration of backpropagation learning using optimized learning rate and momentum. Electron. Lett. 29(14), 1288–1289 (1993)
Costa, M.A., Braga, A., de Menezes, B.R.: Improving neural networks generalization with new constructive and pruning methods. J. Intell. Fuzzy Syst. 13, 75–83 (2003)
Dahl, G., McAvinney, A., Newhall, T.: Parallelizing neural network training for cluster systems. In: Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks (2008)
daviddlewis: Reuters21578 data set. http://www.daviddlewis.com/resources/testcollections/reuters21578 (2010)
Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nedellec, C., Rouveirol, C. (Eds.) Proceedings of the 10th European Conference on Machine Learning (ECML’98), pp. 137–142, Springer, Berlin (1998)
Kontar, S.: Parallel training of neural network for speech recognition. In: Proceedings of the 12th International Conference on, Soft Computing (2006)
Kramer, A.H., Sangiovanni-Vincentelli, A.: Efficient parallel learning algorithms for neural networks. In: Touretzky, S. (Ed.) Advances in Neural Information Processing Systems, pp. 40–48 (1989)
Lai, K.K., Yu, L., Wang, S.: Neural network metalearning for parallel textual information retrieval. Int. Jo. Artif. Intell. 1(A08), 173–184 (2008)
Lewis, D.D.: Naive (Bayes) at forty. The independence assumption in information retrieval. In: Proceedings of the 10th European Conference on, Machine Learning (ECML’98), pp. 4–15 (1998)
Lewis, D.D., Gale, W.A.: A sequential algorithm for training text classifiers. In: SIGIR ’94 Proceedings of the 17th Annual International ACM SIGIR Conference, pp. 3–12 (1994)
Li, C.H., Park, S.C.: Combination of modified bpnn algorithms and an efficient feature selection method for text categorization. Inf. Process. Manag. 45, 329–340 (2009)
Li, C.H., Park, S.C.: An efficient document classification model using an improved back propagation neural network and singular value decomposition. Expert Syst. Appl. 36(2), 3208–3215 (2009)
Lin, M., Ding, C.: Parallel genetic algorithms for dvs scheduling of distributed embedded systems. High Perform. Comput. Commun. LNCS 4782, 180–191 (2007)
McCallum, A., Nigam, K.: A comparison of event models for naive bayes text classification. In: AAAI’98 Workshop on Learning for Text Categorization, pp. 41–48 (1998)
Porter, M.F.: An algorithm for suffix stripping. Program 14(3), 130–137 (1980)
Skucas, I., Remeikis, N., Melninkaite, V.: A combined neural network and decision tree approach for text categorization. Inf. Syst. Dev. XXVII, 173–184 (2005)
Srinivasan, P., Ruiz, M.E.: Automatic text categorization using neural network. In: Proceedings of the 8th ASIS SIG/CR Workshop on Classification Research, pp. 59–72 (1998)
Tamura, H., Ishii, M., Wang, X.G., Tang, Z., Sun, W.D.: An improved backpropagation algorithm to avoid the local minima problem. Neurocomputing 56, 455–460 (2004)
Tan, S.B.: An effective refinement strategy for KNN text classifier. Expert Syst. Appl. 30(2), 290–298 (2006)
Windheuser, U., Zick, F.K., Krahl, D.: Data Mining–Einsatz Inder Praxis. Addison Wesley/Longman, Bonn (1998)
Yam, J.Y.F., Chow, T.W.S.: A weight initialization method for improving training speed in feed forward neural network. IEEE Trans. Neural Netw. 2(30), 219–232 (2000)
Yang, L.T., Xu, L., Lin, M.: Integer factorization by a parallel gnfs algorithm for public key cryptosystems. Embed. Softw. Syst. LNCS 3820, 683–695 (2005)
Zelikovitz, S., Hirsh, H.: Using lsi for text classification in the presence of background text. In: Proceedings of the Tenth International Conference on Information and Knowledge Management, pp. 113–118, ACM Press (2001)
Zeng, H.J., Lu, Y.C., Shi, C.Y., Sun, J.T., Chen, Z., Ma, W.Y.: Supervised latent semantic indexing for document categorization. In: ICDM, pp. 535–538. IEEE Press (2004)
Acknowledgments
This work was supported by NSERC (Natural Sciences and Engineering Research Council, Canada) and CFI (Canadian Foundation of Innovation).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, C.H., Yang, L.T. & Lin, M. Parallel Training of An Improved Neural Network for Text Categorization. Int J Parallel Prog 42, 505–523 (2014). https://doi.org/10.1007/s10766-013-0245-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10766-013-0245-x