Status已發表Published
HNS: Hierarchical negative sampling for network representation learning
Chen, J; Gong, Z. G.; Wang, W; Liu, W
2021
Source PublicationInformation Science
ISSN0020-0255
Pages343-356
AbstractNetwork representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks.
KeywordRepresentation Learning
URLView the original
Language英語English
The Source to ArticlePB_Publication
PUB ID59950
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorGong, Z. G.
Recommended Citation
GB/T 7714
Chen, J,Gong, Z. G.,Wang, W,et al. HNS: Hierarchical negative sampling for network representation learning[J]. Information Science,2021:343-356.
APA Chen, J,Gong, Z. G.,Wang, W,&Liu, W.(2021).HNS: Hierarchical negative sampling for network representation learning.Information Science,343-356.
MLA Chen, J,et al."HNS: Hierarchical negative sampling for network representation learning".Information Science (2021):343-356.
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
[Chen, J]'s Articles
[Gong, Z. G.]'s Articles
[Wang, W]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, J]'s Articles
[Gong, Z. G.]'s Articles
[Wang, W]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, J]'s Articles
[Gong, Z. G.]'s Articles
[Wang, W]'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.