Residential Collegefalse
Status已發表Published
Zero-shot Node Classification with Decomposed Graph Prototype Network
Zheng Wang1,2; Jialong Wang1; Yuchen Guo3; Zhiguo Gong1
2021-08-14
Conference Name27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2021
Source PublicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Pages1769-1779
Conference Date14-18 August 2021
Conference PlaceVirtual, Online
Abstract

Node classification is a central task in graph data analysis. Scarce or even no labeled data of emerging classes is a big challenge for existing methods. A natural question arises: can we classify the nodes from those classes that have never been seen? In this paper, we study this zero-shot node classification (ZNC) problem which has a two-stage nature: (1) acquiring high-quality class semantic descriptions (CSDs) for knowledge transfer, and (2) designing a well generalized graph-based learning model. For the first stage, we give a novel quantitative CSDs evaluation strategy based on estimating the real class relationships, to get the "best"CSDs in a completely automatic way. For the second stage, we propose a novel Decomposed Graph Prototype Network (DGPN) method, following the principles of locality and compositionality for zero-shot model generalization. Finally, we conduct extensive experiments to demonstrate the effectiveness of our solutions.

KeywordNode Classification Graph Convolutional Networks Graph Data Analysis
DOI10.1145/3447548.3467230
URLView the original
Indexed ByCPCI-S
Language英語English
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS IDWOS:000749556801079
Scopus ID2-s2.0-85114954302
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionTHE STATE KEY LABORATORY OF INTERNET OF THINGS FOR SMART CITY (UNIVERSITY OF MACAU)
Faculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorZhiguo Gong
Affiliation1.State Key Laboratory of Internet of Things for Smart City, University of Macau, China
2.Department of Computer Science and Technology, University of Science and Technology, Beijing, China
3.Institute for Brain and Cognitive Sciences, BNRist, Tsinghua University, China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Zheng Wang,Jialong Wang,Yuchen Guo,et al. Zero-shot Node Classification with Decomposed Graph Prototype Network[C], 2021, 1769-1779.
APA Zheng Wang., Jialong Wang., Yuchen Guo., & Zhiguo Gong (2021). Zero-shot Node Classification with Decomposed Graph Prototype Network. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1769-1779.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zheng Wang]'s Articles
[Jialong Wang]'s Articles
[Yuchen Guo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zheng Wang]'s Articles
[Jialong Wang]'s Articles
[Yuchen Guo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zheng Wang]'s Articles
[Jialong Wang]'s Articles
[Yuchen Guo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.