Boosting Multi-Task Weak Learners with Applications to Textual and Social DataReport as inadecuate

Boosting Multi-Task Weak Learners with Applications to Textual and Social Data - Download this document for free, or read online. Document in PDF available to download.

1 Xerox Research Centre Europe Meylan 2 LIFL - Laboratoire d-Informatique Fondamentale de Lille 3 MOSTRARE - Modeling Tree Structures, Machine Learning, and Information Extraction LIFL - Laboratoire d-Informatique Fondamentale de Lille, Inria Lille - Nord Europe 4 GRAppA - LIFL - Groupe de Recherche en Apprentissage Automatique

Abstract : Learning multiple related tasks from data simultaneously can improve predictive performance relative to learning these tasks independently. In this paper we propose a novel multi-task learning algorithm called MT-Adaboost: it extends Adaboost algorithm to the multi-task setting; it uses as multi-task weak classifier a multi-task decision stump. This allows to learn different dependencies between tasks for different regions of the learning space. Thus, we relax the conventional hypothesis that tasks behave similarly in the whole learning space. Moreover, MT-Adaboost can learn multiple tasks without imposing the constraint of sharing the same label set and-or examples between tasks. A theoretical analysis is derived from the analysis of the original Adaboost. Experiments for multiple tasks over large scale textual data sets with social context Enron and Tobacco give rise to very promising results.

Keywords : Textual and social data Multi-task learning Boosting Decision trees Textual and social data.

Author: Jean-Baptiste Faddoul - Boris Chidlovskii - Fabien Torre - Rémi Gilleron -



Related documents