Bandit-Based Structure Learning for Bayesian Network Classifiers
In this work, we tackle the problem of structure learning for Bayesian network classifiers (BNC). Searching for an appropriate structure is a challenging task since the number of possible structures grows exponentially with the number of attributes. We formulate this search problem as a large Markov Decision Process (MDP). This allows us to tackle the problem using sequential decision making methods. Furthermore, we devise a Monte Carlo tree search algorithm to find a tractable solution for the MDP. The use of bandit-based action selection strategy enables us to have a systematic way of guiding the search, making the search in the large space of unrestricted structures tractable. The results of classification on different datasets show that the use of this method can significantly boost the performance of structure learning for BNCs.
KeywordsBayesian network classifier Structure learning Reinforcement learning Bandit methods Monte Carlo tree search
Unable to display preview. Download preview PDF.
- 2.Carvalho, A.M., Roos, T.T., Oliveira, A.L., Myllymäki, P., et al.: Discriminative learning of bayesian networks via factorized conditional log-likelihood. Journal of Machine Learning Research (2011)Google Scholar
- 3.Fayyad, U., Irani, K.: Multi-interval discretization of continuous-valued attributes for classification learning (1993)Google Scholar
- 5.Gaudel, R., Sebag, M., et al.: Feature selection as a one-player game (2010)Google Scholar
- 6.Gelly, S., Wang, Y.: Exploration exploitation in go: Uct for monte-carlo go. In: Twentieth Annual Conference on Neural Information Processing Systems (NIPS) (2006)Google Scholar
- 8.Grossman, D., Domingos, P.: Learning bayesian network classifiers by maximizing conditional likelihood. In: Proceedings of the Twenty-First International Conference on Machine Learning (2004)Google Scholar
- 9.Keogh, E., Pazzani, M.: Learning augmented bayesian classifiers: A comparison of distribution-based and classification-based approaches. In: Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics, pp. 225–230. Citeseer (1999)Google Scholar
- 12.Pernkopf, F., Wohlmayr, M., Tschiatschek, S.: Maximum margin bayesian network classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence (2012)Google Scholar
- 13.Su, J., Zhang, H., Ling, C.X., Matwin, S.: Discriminative parameter learning for bayesian networks. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1016–1023 (2008)Google Scholar