PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning from relevant tasks only
Samuel Kaski and Jaakko Peltonen
In: Machine Learning: ECML 2007 (Proceedings of the 18th European Conference on Machine Learning) (2007) Springer-Verlag , Berlin , pp. 608-615.

Abstract

We introduce a problem called relevant subtask learning, a variant of multi-task learning. The goal is to build a classifier for a task-of-interest having too little data. We also have data for other tasks but only some are relevant, meaning they contain samples classified in the same way as in the task-of-interest. The problem is how to utilize this ``background data'' to improve the classifier in the task-of-interest. We show how to solve the problem for logistic regression classifiers, and show that the solution works better than a comparable multi-task learning model. The key is to assume that data of all tasks are mixtures of relevant and irrelevant samples, and model the irrelevant part with a sufficiently flexible model such that it does not distort the model of relevant data.

EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
Information Retrieval & Textual Information Access
ID Code:3554
Deposited By:Samuel Kaski
Deposited On:11 February 2008