You are not logged in.
Openly accessible

Column networks for collective classification

Pham, Trang, Tran, Truyen, Phung, Dinh and Venkatesh, Svetha 2017, Column networks for collective classification, in AAAI-17: Proceedings of the 31st Artificial Intelligence AAAI Conference, AAAI Press, Palo Alto, Calif., pp. 2485-2491.

Attached Files
Name Description MIMEType Size Downloads
pham-columnnetworks-2017.pdf Published version application/pdf 674.52KB 7

Title Column networks for collective classification
Author(s) Pham, Trang
Tran, TruyenORCID iD for Tran, Truyen orcid.org/0000-0001-6531-8907
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 Artificial Intelligence. AAAI Conference (31st : 2017: San Francisco, California)
Conference location San Francisco, California
Conference dates 4-9 Feb. 2017
Title of proceedings AAAI-17: Proceedings of the 31st Artificial Intelligence AAAI Conference
Publication date 2017
Conference series AAAI Conference on Artificial Intelligence
Start page 2485
End page 2491
Total pages 7
Publisher AAAI Press
Place of publication Palo Alto, Calif.
Summary Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy than non-collective classifiers, collective classification is computationally challenging and has not leveraged on the recent breakthroughs of deep learning. We present Column Network (CLN), a novel deep learning model for collective classification in multi-relational domains. CLN has many desirable theoretical properties: (i) it encodes multi-relations between any two instances; (ii) it is deep and compact, allowing complex functions to be approximated at the network level with a small set of free parameters; (iii) local and relational features are learned simultaneously; (iv) long-range, higher-order dependencies between instances are supported naturally; and (v) crucially, learning and inference are efficient with linear complexity in the size of the network and the number of relations. We evaluate CLN on multiple real-world applications: (a) delay prediction in software projects, (b) PubMed Diabetes publication classification and (c) film genre classification. In all of these applications, CLN demonstrates a higher accuracy than state-of-the-art rivals.
Language eng
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 0 Not Applicable
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Grant ID DP150100031
Copyright notice ©2017, AAAI
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30096792

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

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.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 64 Abstract Views, 10 File Downloads  -  Detailed Statistics
Created: Tue, 30 May 2017, 15:44:19 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.