Meta-Mining Evaluation Framework : A large scale proof of concept on Meta-Learning

William Raynaut (1) , Chantal Soulé-Dupuy (1, 2) , Nathalie Vallès-Parlangeau (1, 2)

1 IRIT-SIG - Systèmes d’Informations Généralisées
2 UT Capitole - Université Toulouse Capitole

This paper aims to provide a unified framework for the evaluation and comparison of the many emergent meta-mining techniques. This framework is illustrated on the case study of the meta-learning problem in a large scale experiment. The results of this experiment are then explored through hypothesis testing in order to provide insight regarding the performance of the different meta-learning schemes, advertising the potential of our approach regarding meta-level knowledge discovery.

Mots clés: Hypothesis testing; Knowledge discovery; Meta-learning; Meta-mining; Evaluation criterion

Domaines: Théorie de l'information [cs.IT]; Recherche d'information [cs.IR]

William Raynaut, Chantal Soulé-Dupuy, Nathalie Vallès-Parlangeau. Meta-Mining Evaluation Framework : A large scale proof of concept on Meta-Learning. 29th Australian Conference on Artificial Intelligence 2016 (AI 2016), Dec 2016, Hobart, Australia. pp.215-228, ⟨10.1007/978-3-319-50127-7_18⟩. ⟨hal-01692700⟩