Curriculum learning of multiple tasks

Pentina, Anastasia, Sharmanska, Viktoriia and Lampert, Christoph H (2015) Curriculum learning of multiple tasks. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7 - 12 Jun 2015. Published in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5492-5500. IEEE ISSN 1063-6919 ISBN 9781467369633

[img] PDF - Published Version
Download (1MB)

Abstract

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover a favourable order of tasks.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 30 Nov 2021 08:57
Last Modified: 30 Nov 2021 08:58
URI: http://sro.sussex.ac.uk/id/eprint/103147

View download statistics for this item

📧 Request an update