Learning high-order task relationships in multi-task learning

Yu ZHANG, Dit Yan Yeung

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

15 Citations (Scopus)

Abstract

Multi-task learning is a way of bringing inductive transfer studied in human learning to the machine learning community. A central issue in multi-task learning is to model the relationships between tasks appropriately and exploit them to aid the simultaneous learning of multiple tasks effectively. While some recent methods model and learn the task relationships from data automatically, only pairwise relationships can be represented by them. In this paper, we propose a new model, called Multi- Task High-Order relationship Learning (MTHOL), which extends in a novel way the use of pairwise task relationships to high-order task relationships. We first propose an alternative formulation of an existing multi-task learning method. Based on the new formulation, we propose a high-order generalization leading to a new prior for the model parameters of different tasks. We then propose a new probabilistic model for multi-task learning and validate it empirically on some benchmark datasets.

Original languageEnglish
Title of host publicationIJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence
Pages1917-1923
Number of pages7
Publication statusPublished - 2013
Event23rd International Joint Conference on Artificial Intelligence, IJCAI 2013 - Beijing, China, Beijing, China
Duration: 3 Aug 20139 Aug 2013

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference23rd International Joint Conference on Artificial Intelligence, IJCAI 2013
Country/TerritoryChina
CityBeijing
Period3/08/139/08/13

Scopus Subject Areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learning high-order task relationships in multi-task learning'. Together they form a unique fingerprint.

Cite this