Threshold-free Pattern Mining Meets Multi-Objective Optimization: Application to Association Rules
Threshold-free Pattern Mining Meets Multi-Objective Optimization: Application to Association Rules
Charles Vernerey, Samir Loudni, Noureddine Aribi, Yahia Lebbah
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 1880-1886.
https://doi.org/10.24963/ijcai.2022/261
Constraint-based pattern mining is at the core of numerous data mining tasks. Unfortunately, thresholds which are involved in these constraints cannot be easily chosen. This paper investigates a Multi-objective Optimization approach where several (often conflicting) functions need to be optimized at the same time. We introduce a new model for efficiently mining Pareto optimal patterns with constraint programming. Our model exploits condensed pattern representations to reduce the mining effort. To this end, we design a new global constraint for ensuring the closeness of patterns over a set of measures. We show how our approach can be applied to derive high-quality non redundant association rules without the use of thresholds whose added-value is studied on both UCI datasets and case study related to the analysis of genes expression data integrating multiple external genes annotations.
Keywords:
Constraint Satisfaction and Optimization: Constraint Programming
Constraint Satisfaction and Optimization: Constraint Optimization
Constraint Satisfaction and Optimization: Constraints and Machine Learning
Data Mining: Exploratory Data Mining
Data Mining: Frequent Pattern Mining