File(s) under permanent embargo
Column networks for collective classification
conference contribution
posted on 2017-02-09, 00:00 authored by Trang Thi Minh Pham, Truyen TranTruyen Tran, Quoc-Dinh Phung, Svetha VenkateshSvetha VenkateshRelational 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.
History
Event
Artificial Intelligence. AAAI Conference (31st : 2017: San Francisco, California)Pagination
2485 - 2491Publisher
AAAI PressLocation
San Francisco, CaliforniaPlace of publication
Palo Alto, Calif.Start date
2017-02-04End date
2017-02-09Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2017, AAAITitle of proceedings
AAAI-17: Proceedings of the 31st Artificial Intelligence AAAI ConferenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC