On better exploring and exploiting task relationships in multitask learning: Joint model and feature learning

Li, Y; Tian, X; Liu, T; Tao, D

On better exploring and exploiting task relationships in multitask learning: Joint model and feature learning

Li, Y Tian, X Liu, T

Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Neural Networks and Learning Systems, 2018, 29 (5), pp. 1975 - 1985
Issue Date:: 2018-05-01

Closed Access

	Filename	Description	Size
	07902220.pdf	Published Version	1.49 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, Y	en_US
dc.contributor.author	Tian, X	en_US
dc.contributor.author	Liu, T https://orcid.org/0000-0002-9640-6472	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2018-05-01	en_US
dc.identifier.citation	IEEE Transactions on Neural Networks and Learning Systems, 2018, 29 (5), pp. 1975 - 1985	en_US
dc.identifier.issn	2162-237X	en_US
dc.identifier.uri	http://hdl.handle.net/10453/123849
dc.description.abstract	© 2012 IEEE. Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations. The objective of our proposed method is to transform the features of different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized. We give a detailed introduction to our proposed MTL method. Additionally, an alternating algorithm is introduced to optimize the nonconvex objection. A theoretical bound is given to demonstrate that the relatedness between tasks can be better measured by our proposed MTL algorithm. We conduct various experiments to verify the superiority of the proposed joint model and feature MTL method.	en_US
dc.relation.ispartof	IEEE Transactions on Neural Networks and Learning Systems	en_US
dc.relation.isbasedon	10.1109/TNNLS.2017.2690683	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	On better exploring and exploiting task relationships in multitask learning: Joint model and feature learning	en_US
dc.type	Journal Article
utslib.citation.volume	5	en_US
utslib.citation.volume	29	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	5	en_US
pubs.publication-status	Published	en_US
pubs.volume	29	en_US

Abstract:

© 2012 IEEE. Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations. The objective of our proposed method is to transform the features of different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized. We give a detailed introduction to our proposed MTL method. Additionally, an alternating algorithm is introduced to optimize the nonconvex objection. A theoretical bound is given to demonstrate that the relatedness between tasks can be better measured by our proposed MTL algorithm. We conduct various experiments to verify the superiority of the proposed joint model and feature MTL method.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/123849