Skip to Main content Skip to Navigation
Conference papers

QLTL: a Simple yet Efficient Algorithm for Semi-Supervised Transfer Learning

Abstract : Most machine learning techniques rely on the assumption that training and target data share a similar underlying distribution. When this assumption is violated, they usually fail to generalise; this is one of the situations tackled by transfer learning: achieving good classification performances on different-but-related datasets. In this paper, we consider the specific case where the task is unique, and where the training set(s) and the target set share a similar-but-different underlying distribution. Our method, QLTL: Quadratic Loss Transfer Learning, constitutes semi-supervised learning: we train a set of classifiers on the available training data in order to input knowledge, and we use a centred kernel polarisation criterion as a way to correct the density probability function shift between training and target data. Our method results in a convex problem, leading to an analytic solution. We show encouraging results on a toy example with covariate shift, and good performances on a text-document classification task, relatively to recent algorithms.
Document type :
Conference papers
Complete list of metadatas
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Wednesday, March 25, 2020 - 10:58:00 PM
Last modification on : Thursday, October 8, 2020 - 4:24:51 PM





Bruno Muller, Régis Lengellé. QLTL: a Simple yet Efficient Algorithm for Semi-Supervised Transfer Learning. 10th International Conference on Pattern Recognition Systems (ICPRS-2019), Jul 2019, Tours, France. pp.6 (30-35), ⟨10.1049/cp.2019.0244⟩. ⟨hal-02519318⟩



Record views