A framework for learning Multiple-Instance Decision Trees and Rule Sets

Yann Chevaleyre 1 Jean-Daniel Zucker 1
1 APA - Apprentissage et Acquisition des connaissances
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper proposes a generic extension to propositional rule learners to handle multiple-instance data. In a multiple-instance representation, each learning example is represented by a bag” of fixed-length feature vectors”.Such a representation,lying somewhere between propositional and first-order representation, offers a tradeoff between the two. Naive-RipperMi is one implementation of this extension on the rule learning algorithm Ripper. Several pitfalls encountered by this naive extension during induction are explained. A new multiple-instance search bias based on decision tree techniques is then used to avoid these pitfalls. Experimental results show the benefits of this approach for solving propositionalized relational problems in terms of speed and accuracy.
Document type :
Conference papers
Complete list of metadatas

Contributor : Lip6 Publications <>
Submitted on : Thursday, August 3, 2017 - 5:14:10 PM
Last modification on : Thursday, March 21, 2019 - 1:09:53 PM

Links full text



Yann Chevaleyre, Jean-Daniel Zucker. A framework for learning Multiple-Instance Decision Trees and Rule Sets. European Conference on Machine Learning, Sep 2001, Freiburg, Germany. pp.49-60, ⟨10.1007/3-540-44795-4_5⟩. ⟨hal-01571854⟩



Record views