Soutenance de thèse : Alexandre MILLOT

Exceptional Model Mining meets Multi-objective Optimization: Application to plant growth recipes in controlled environments

Doctorant : Alexandre MILLOT

Laboratoire INSA : LIRIS

Ecole doctorale : ED512 Informatique Et Mathématiques de Lyon

In today's society, information is becoming ever more pervasive. Designing new Pattern Discovery methods, that allow for the semi-automatic discovery of relevant information and knowledge, is crucial. We consider data made of descriptive attributes, where one or several of these attributes can be considered as target label(s). When a unique target is considered, Subgroup Discovery aims at discovering subsets of objects - subgroups - whose target label distribution significantly deviates from that of the overall data. Exceptional Model Mining is a generalization of Subgroup Discovery that enables the discovery of significant local deviations in complex interactions between several targets. Multi-objective Optimization methods, which find optimal trade-offs between competing objectives, are essential. Although these research fields possess extensive literature, their cross-fertilization has been considered only sparsely. We investigate the design of methods for the discovery of relevant parameter values driving the optimization of a process. Our first contribution is OSMIND, a Subgroup Discovery algorithm that leverages advanced techniques for search space reduction to return an optimal pattern in purely numerical data. Our second contribution consists of a generic iterative framework that leverages the actionability of Subgroup Discovery to solve optimization problems. Our third and main contribution is Exceptional Pareto Front Mining, a new class of models for Exceptional Model Mining that involves cross-fertilization between Pattern Discovery and Multi-objective Optimization. Empirical studies have been carried out on each contribution to illustrate their relevance. Our methods are generic and can be applied to many application domains.
To assess the actionability of our contributions in real life, we consider plant growth recipe optimization in controlled environments, the application scenario that has motivated our work. It is an intrinsic Multi-objective optimization problem. On synthetic and real-life data, we show that our methods allow for the discovery of parameter values that optimize the yield-cost trade-off of growth recipes.