The Membership Problem for Probabilistic and Data Dependencies
It has been suggested that Bayesian networks and relational databases are different because the membership problems for probabilistic conditional independence and embedded multivalued dependency do not always coincide. The present study indicates that the membership problems coincide on solvable classes of dependencies and differ on unsolvable classes. We therefore maintain that Bayesian networks and relational databases are the same in a practical sense, since only solvable classes of dependencies are useful in the design and implementation of both knowledge systems.
KeywordsBayesian Network Relational Database Database Model Practical Sense Probabilistic Dependency
Unable to display preview. Download preview PDF.
- 1.C. Beeri, R. Fagin, and J.H. Howard. A complete axiomatization for functional and multivalued dependencies in database relations. In Proceedings of ACMSIGMOD International Conference on Management of Data, pages 47–61, 1977.Google Scholar
- 3.D. Maier. The Theory of Relational Databases. Principles of Computer Science. Computer Science Press, Rockville, Maryland, 1983.Google Scholar
- 5.D. Parker and K. Parsaye-Ghomi. Inference involving embedded multivalued dependencies and transitive dependencies. In Proceedings of ACM-SIGMOD International Conference on Management of Data, pages 52–57, 1980.Google Scholar
- 6.J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers, San Francisco, California, 1988.Google Scholar
- 7.Y. Sagiv and F. Walecka. Subset dependencies and a complete result for a subclass of embedded multivalued dependencies. Journal of the ACM,20(1):103117, 1982.Google Scholar
- 9.M. Studeny. Conditional independence relations have no finite complete characterization. In Eleventh Prague Conference on Information Theory, Statistical Decision Foundation and Random Processes, pages 377–396. Kluwer, 1990.Google Scholar
- 10.S.K.M. Wong. Testing implication of probabilistic dependencies. In Twelfth Conference on Uncertainty in Artificial Intelligence, pages 545–553. Morgan Kaufmann Publishers, 1996.Google Scholar
- 12.S.K.M. Wong, C.J. Butz, and D. Wu. On the implication problem for probabilistic conditional independency IEEE Transactions on Systems Man and CyberneticsVol. 30, Part A, No. 6, 785–805, 2000 Google Scholar
- 13.S.K.M. Wong, C.J. Butz, and Y. Xiang. A method for implementing a probabilistic model as a relational database. In Eleventh Conference on Uncertainty in Artificial Intelligencepages 556–564. Morgan Kaufmann Publishers, 1995 Google Scholar
- 14.S.K.M. Wong and Z.W. Wang. On axiomatization of probabilistic conditional independence. In Tenth Conference on Uncertainty in Artificial Intelligence, pages 591–597. Morgan Kaufmann Publishers, 1994.Google Scholar