An important task of knowledge discovery deals with discovering association rules. This very general model has been widely studied and efficient algorithms have been proposed. But most of the time, only frequent rules are seeked. Here we propose to consider this problem as a multi-objective combinatorial optimization problem in order to be able to also find non frequent but interesting rules. As the search space may be very large, a discussion about different approaches is proposed and a hybrid approach that combines a metaheuristic and an exact operator is presented.
Mots-clés : hybridization, multi-objective optimization, knowledge discovery, association rules
@article{RO_2008__42_1_69_0, author = {Khabzaoui, Mohammed and Dhaenens, Clarisse and Talbi, El-Ghazali}, title = {Combining evolutionary algorithms and exact approaches for multi-objective knowledge discovery}, journal = {RAIRO - Operations Research - Recherche Op\'erationnelle}, pages = {69--83}, publisher = {EDP-Sciences}, volume = {42}, number = {1}, year = {2008}, doi = {10.1051/ro:2008004}, mrnumber = {2400275}, zbl = {1170.90476}, language = {en}, url = {http://www.numdam.org/articles/10.1051/ro:2008004/} }
TY - JOUR AU - Khabzaoui, Mohammed AU - Dhaenens, Clarisse AU - Talbi, El-Ghazali TI - Combining evolutionary algorithms and exact approaches for multi-objective knowledge discovery JO - RAIRO - Operations Research - Recherche Opérationnelle PY - 2008 SP - 69 EP - 83 VL - 42 IS - 1 PB - EDP-Sciences UR - http://www.numdam.org/articles/10.1051/ro:2008004/ DO - 10.1051/ro:2008004 LA - en ID - RO_2008__42_1_69_0 ER -
%0 Journal Article %A Khabzaoui, Mohammed %A Dhaenens, Clarisse %A Talbi, El-Ghazali %T Combining evolutionary algorithms and exact approaches for multi-objective knowledge discovery %J RAIRO - Operations Research - Recherche Opérationnelle %D 2008 %P 69-83 %V 42 %N 1 %I EDP-Sciences %U http://www.numdam.org/articles/10.1051/ro:2008004/ %R 10.1051/ro:2008004 %G en %F RO_2008__42_1_69_0
Khabzaoui, Mohammed; Dhaenens, Clarisse; Talbi, El-Ghazali. Combining evolutionary algorithms and exact approaches for multi-objective knowledge discovery. RAIRO - Operations Research - Recherche Opérationnelle, Tome 42 (2008) no. 1, pp. 69-83. doi : 10.1051/ro:2008004. http://www.numdam.org/articles/10.1051/ro:2008004/
[1] Fast algorithms for mining association rules, in Proc. 20th Int. Conf. Very Large Data Bases, VLDB, edited by J.B. Bocca, M. Jarke, and C. Zaniolo, Morgan Kaufmann 12 (1994) 487-499
and ,[2] A Parallel Genetic Algorithm for Rule Discovery in Large Databases, in Proc. 1999 IEEE Systems, Man and Cybernetics Conf., Vol. III (1999) 940-945, Tokyo, Japan.
, and ,[3] Adaptive mechanisms for multi-objective evolutionary algorithms. IMACS multiconference, Computational Engineering in Systems Applications (CESA'03), IEEE Service Center, Piscataway, New Jersey, S3-R-00-222:100-107 (2003).
, and ,[4] Efficient implementations of apriori and eclat, in Workshop Frequent Item Set Mining Implementations (FIMI 2003, Melbourne, FL, USA) 90 (2003).
,[5] Evolutionary Algorithms for Solving Multi-Objective Problems. Kluwer Academic Publishers (2002). | MR | Zbl
, and ,[6] Embedding branch and bound within evolutionary algorithms. Appl. Intell. 18 (2003) 137-153 | Zbl
and ,[7] An overview of evolutionary algorithms in multiobjective optimization. Evolutionary Comput. 3 (1995) 1-16.
and ,[8] On rule interestingness measures. Knowledge-Based Syst. J. 12 (1999) 309-315.
,[9] Knowledge discovery and interestingness measures: A survey, technical report cs 99-04. Technical report, Department of Computer Science, University of Regina, October (1999).
and ,[10] Simultaneously applying multiple mutation operators in genetic algorithms. J. Heuristics 6 (2000) 439-455. | Zbl
, and ,[11] On the performance of multiple objective genetic local search on the 0/1 knapsack problem. a comparative experiment. Technical Report RA-002/2000, Institute of Computing Science, Poznan University of Technology, Poznan, Poland (2000).
,[12] Etude exploratoire des critères de qualité des règles d'association en datamining, in Journées Françaises de Statistique (2003) 583-587.
, , and ,[13] Association rules discovery for DNA microarray data. Bioinformatics Workshop of SIAM International Conference on Data Mining (2004) 63-71.
, and ,[14] A Multicriteria Genetic Algorithm to analyze DNA microarray data, in Congress on Evolutionary Computation (CEC), Vol. II, pp. 1874-1881, Portland, USA (2004). IEEE Service center.
, and ,[15] On the assessment of multiobjective approaches to the adaptive distributed database management problem. In Proceedings of the Sixth International Conference on Parallel Problem Solving from Nature (PPSN VI) (2000) 869-878
, and ,[16] Combining metaheuristics and exact algorithms in combinatorial optimization: A survey and classification, in First international Work-Conference on the Interplay between Natural and Artificial Computation (IWINAC) 3562 (2005) 41-53.
and ,[17] Knowledge Discovery in Databases, Chapter Rule Induction Using Information Theory, G. Piatetsky-Shapiro and J. Frawley (1991) 159-176.
and ,[18] A taxonomy of hybrid metaheuristics. Journal of Heuristics 8 (2002) 541-564.
,[19] Selecting the right interestingness measure for association patterns, in Proceedings of the Eight ACM SIGKDD conference, Edmonton, Canada (2002).
, and ,[20] On measuring multiobjective evolutionary algorithm performance, in In 2000 Congress on Evolutionary Computation. Piscataway, New Jersey, Vol. 1, 204-211 (2000).
and ,[21] Interestingness-based interval merger for numeric association rules, in edited by Proc. 4th Int. Conf. Knowledge Discovery and Data Mining, KDD, R. Agrawal, P. E. Stolorz, and G. Piatetsky-Shapiro, pp. 121-128. AAAI Press, (1998) 27-31. New York, USA.
, and ,[22] Parallel sequence mining on shared-memory machines. J. Parallel and Distrib. Comput. 61 (2001) 401-426. | Zbl
,[23] Multiobjective evolutionary algorithms: A comparative case study and the strength pareto approach. IEEE Trans. Evol. Comput. 3 (1999) 257-271.
and ,Cité par Sources :