The Computational Complexity of Inference Using Rough Set Flow Graphs
Pawlak recently introduced rough set flow graphs (RSFGs) as a graphical framework for reasoning from data. Each rule is associated with three coefficients, which have been shown to satisfy Bayes’ theorem. Thereby, RSFGs provide a new perspective on Bayesian inference methodology.
In this paper, we show that inference in RSFGs takes polynomial time with respect to the largest domain of the variables in the decision tables. Thereby, RSFGs provide an efficient tool for uncertainty management. On the other hand, our analysis also indicates that a RSFG is a special case of conventional Bayesian network and that RSFGs make implicit assumptions regarding the problem domain.
KeywordsBayesian Network Directed Acyclic Graph Problem Domain Joint Probability Distribution Decision Table
Unable to display preview. Download preview PDF.
- 3.Greco, S., Pawlak, Z., Slowinski, R.: Generalized Decision Algorithms, Rough Inference Rules and Flow Graphs. In: The Third International Conference on Rough Sets, and Current Trends in Computing, pp. 93–104 (2002)Google Scholar
- 4.Horvitz, E., Barry, E.M.: Display of Information for Time Critical Decision Making. In: Proceedings of Eleventh Conference on Uncertainty in Artificial Intelligence, pp. 296–305. Morgan Kaufmann, San Francisco (1995)Google Scholar
- 5.Horvitz, E., Breese, J., Heckerman, D., Hovel, D., Rommelse, K.: The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users. In: Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, Madison, WI, pp. 256–265 (1998)Google Scholar
- 6.Pawlak, Z.: Flow Graphs and Decision Algorithms. In: The Ninth International Conference on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing, pp. 1–10 (2003)Google Scholar
- 7.Pawlak, Z.: In Pursuit of Patterns in Data Reasoning from Data - The Rough Set Way. In: The Third International Conference on Rough Sets, and Current Trends in Computing, pp. 1–9 (2002)Google Scholar
- 10.Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
- 11.Pearl, J.: Reverend Bayes on Inference Engines: A Distributed Heirarchical Approach, pp. 133–136. AAAI, Menlo Park (1982)Google Scholar
- 12.Shafer, G.: Probabilistic Expert Systems. Society for the Institute and Applied Mathematics, Philadelphia (1996)Google Scholar