You are not logged in.

What shall i share and with whom? A multi-task learning formulation using multi-faceted task relationships

Gupta, Sunil, Rana, Santu, Phung, Dinh and Venkatesh, Svetha 2015, What shall i share and with whom? A multi-task learning formulation using multi-faceted task relationships, in SDM 2015: Proceedings of the 15th SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics, [Vancouver, British Columbia], pp. 703-711, doi: 10.1137/1.9781611974010.79.

Attached Files
Name Description MIMEType Size Downloads

Title What shall i share and with whom? A multi-task learning formulation using multi-faceted task relationships
Author(s) Gupta, SunilORCID iD for Gupta, Sunil orcid.org/0000-0002-3308-1930
Rana, SantuORCID iD for Rana, Santu orcid.org/0000-0003-2247-850X
Phung, DinhORCID iD for Phung, Dinh orcid.org/0000-0002-9977-8247
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name International Conference on Data Mining (15th : 2015 : Vancouver, British Columbia)
Conference location Vancouver, British Columbia
Conference dates 30 Apr.-2 May. 2015
Title of proceedings SDM 2015: Proceedings of the 15th SIAM International Conference on Data Mining
Publication date 2015
Start page 703
End page 711
Total pages 9
Publisher Society for Industrial and Applied Mathematics
Place of publication [Vancouver, British Columbia]
Summary Multi-task learning is a learning paradigm that improves the performance of "related" tasks through their joint learning. To do this each task answers the question "Which other task should I share with"? This task relatedness can be complex - a task may be related to one set of tasks based on one subset of features and to other tasks based on other subsets. Existing multi-task learning methods do not explicitly model this reality, learning a single-faceted task relationship over all the features. This degrades performance by forcing a task to become similar to other tasks even on their unrelated features. Addressing this gap, we propose a novel multi-task learning model that leams multi-faceted task relationship, allowing tasks to collaborate differentially on different feature subsets. This is achieved by simultaneously learning a low dimensional sub-space for task parameters and inducing task groups over each latent subspace basis using a novel combination of L1 and pairwise L∞ norms. Further, our model can induce grouping across both positively and negatively related tasks, which helps towards exploiting knowledge from all types of related tasks. We validate our model on two synthetic and five real datasets, and show significant performance improvements over several state-of-the-art multi-task learning techniques. Thus our model effectively answers for each task: What shall I share and with whom?
ISBN 9781611974010
Language eng
DOI 10.1137/1.9781611974010.79
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, Society for Industrial and Applied Mathematics
Persistent URL http://hdl.handle.net/10536/DRO/DU:30082939

Document type: Conference Paper
Collection: Centre for Pattern Recognition and Data Analytics
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 166 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Tue, 19 Apr 2016, 18:54:30 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.