Skip to Main content Skip to Navigation
Conference papers

A phase transition-based perspective on multiple instance kernels

Abstract : This paper is concerned with Relational Support Vector Machines, at the intersection of Support Vector Machines (SVM) and Inductive Logic Programming or Relational Learning. The so-called phase transition framework, originally developed for constraint satisfaction problems, has been extended to relational learning and it has provided relevant insights into the limitations and difficulties thereof. The goal of this paper is to examine relational SVMs and specifically Multiple Instance (MI) Kernels along the phase transition framework. A relaxation of the MI-SVM problem formalized as a linear programming problem (LPP) is defined and we show that the LPP satisfiability rate induces a lower bound on the MI-SVM generalization error. An extensive experimental study shows the existence of a critical region, where both LPP unsatisfiability and MI-SVM error rates are high. An interpretation for these results is proposed.
Document type :
Conference papers
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Archive Ouverte Prodinra Connect in order to contact the contributor
Submitted on : Wednesday, June 3, 2020 - 7:09:52 PM
Last modification on : Tuesday, June 15, 2021 - 2:57:04 PM
Long-term archiving on: : Saturday, December 5, 2020 - 12:16:56 AM


Publisher files allowed on an open archive



Romaric Gaudel, Michèle Sebag, Antoine Cornuéjols. A phase transition-based perspective on multiple instance kernels. Plate-forme AFIA 2007: Conférence francophone sur l'Apprentissage automatique, Jul 2007, Grenoble, France. ⟨10.1007/978-3-540-78469-2_14⟩. ⟨hal-01197534⟩



Record views


Files downloads