Decremental and Incremental Reshaping of Algebraic Bayesian Networks Global Structures
The paper considers algorithms for global structures generation in algebraic Bayesian networks. A decremental algorithm for constructing a secondary structure after deleting vertex from the adjacency graph is proposed supplemented by a listing of the algorithm code and by the proof of its correctness. The results of the statistical tests for decremental algorithm are proposed graphically together with a comparative analysis of the results. Moreover, the description of incremental algorithm for adding vertex in tertiary structure is provided supplemented by a listing of the algorithm code and proof of its correctness.
KeywordsJoint graph Probabilistic graphical model Incremental algorithm Performance statistical estimate Structure learning Machine learning
The paper presents results of the project partially supported with RFBR grant 15-01-09,001-a “Combined Probabilistic-Logic Graphical Approach to Representation and Processing of Unsertain Knowledge Systems: Algebraical Bayesian Networks and Related Models”, and partially supported by the Government of the Russian Federation, Grant 074-U01.
- 3.Leonelli, M., Smith, J.: Bayesian decision support for complex systems with many distributed experts. Ann. Oper. Res. 235(1) (2015)Google Scholar
- 5.Oparin, V.V., Filchenkov, A.A., Sirotkin, A.V., Tulupyev, A.L.: Matroidal representation for the adjacency graphs family built on a set of knowledge patterns. Sci. Tech. J. Inf. Technol. Mech. Opt. (4), 73–76 (2009). http://ntv.ifmo.ru/file/article/697.pdf (In Russian)
- 6.Oparin, V.V., Tulupyev, A.L.: Synthesis of a joint graph with minimal number of edges: an algorithm formalization and a proof of correctness. Tr. SPIIRAN (11), 142–157 (2009).http://mi.mathnet.ru/trspy52 (In Russian)
- 7.Tulupyev, A.L.: Join tree with conjunctions ideals as an acyclic algebraic bayesian network. Tr. SPIIRAN (3), 198–227 (2006). http://mi.mathnet.ru/trspy222 (In Russian)
- 8.Tulupyev, A.L.: Algebraic bayesian networks: global probabilistic-logic inference in adjacent tree (2007) (In Russian)Google Scholar
- 9.Tulupyev, A.L., Nikolenko, S.I., Sirotkin, A.V.: Bayesian Networks: a Probabilistic-logic Approach. SPb: Nauka (2006) (In Russian)Google Scholar
- 10.Tulupyev, A.L., Sirotkin, A.V., Nikolenko, S.I.: Bayesian Belief Networks. SPb: SPbSU Press (2009) (In Russian)Google Scholar
- 11.Yue, K., Fang, Q., Wang, X., Li, J., Liu, W.: A parallel and incremental approach for data-intensive learning of bayesian networks. IEEE Trans. Cybern. 45(12) (2015)Google Scholar
- 12.Zhu, M., Liu, S.: A decomposition algorithm for learning bayesian networks based on scoring function. J. Appl. Math.Google Scholar
- 13.Zotov, M.A., Tulupyev, A.L., Sirotkin, A.V.: Complexity statistical estimates of straightforward and greedy algorithms for algebraic Bayesian networks syntesis. Nechetkie Sistemy i Myagkie Vychisleniya [Fuzzy Systems and Soft Computing] 10(1), 75–91 (2015) (In Russian)Google Scholar
- 14.Zotov, M., Levenets, D., Tulupyev, A., Zolotin, A.: Synthesis of the secondary structure of algebraic bayesian networks: an incremental algorithm and statistical estimation of its complexity. Tr. SPIIRAN 16(1), 122–132 (2016) (In Russian)Google Scholar
- 15.Zotov, M., Tulupyev, A.: Secondary structure synthesis in algebraic bayesian networks: a statistical technique for complexity estimates and comparative analysis of greedy and straightforward algorithms. Comput. Tools Educ. 1, 3–18 (2015) (In Russian)Google Scholar