Learning multi-level task groups in multi-task learning

Lei Han, Yu Zhang

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

42 Citations (Scopus)

Abstract

In multi-task learning (MTL), multiple related tasks are learned jointly by sharing information across them. Many MTL algorithms have been proposed to learn the underlying task groups. However, those methods are limited to learn the task groups at only a single level, which may be not sufficient to model the complex structure among tasks in many real-world applications. In this paper, we propose a Multi-Level Task Grouping (MeTaG) method to learn the multi-level grouping structure instead of only one level among tasks. Specifically, by assuming the number of levels to be H, we decompose the parameter matrix into a sum of H component matrices, each of which is regularized with a l1 norm on the pairwise difference among parameters of all the tasks to construct level-specific task groups. For optimization, we employ the smoothing proximal gradient method to efficiently solve the objective function of the MeTaG model. Moreover, we provide theoretical analysis to show that under certain conditions the MeTaG model can recover the true parameter matrix and the true task groups in each level with high probability. We experiment our approach on both synthetic and real-world datasets, showing competitive performance over state-of-the-art MTL methods.

Original languageEnglish
Title of host publicationProceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
PublisherAAAI press
Pages2638-2644
Number of pages7
ISBN (Print)9781577356981
DOIs
Publication statusPublished - 1 Mar 2015
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015 - Austin, United States, Austin, United States
Duration: 25 Jan 201530 Jan 2015
https://ojs.aaai.org/index.php/AAAI/issue/view/304
https://ojs.aaai.org/index.php/AAAI/issue/view/483

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number1
Volume29
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
Country/TerritoryUnited States
CityAustin
Period25/01/1530/01/15
Internet address

Scopus Subject Areas

  • Software
  • Artificial Intelligence

User-Defined Keywords

  • Multi-Task Learning
  • Task Grouping
  • Multi-Level

Fingerprint

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

Cite this