Home >

news Help

Publication Information


Title
Japanese: 
English:Measuring Graph Reconstruction Precisions---How Well Do Embeddings Preserve the Graph Proximity Structure 
Author
Japanese: Liu Xin, 村田剛志, Kyoung-Sook Kim.  
English: Liu Xin, Tsuyoshi MURATA, Kyoung-Sook Kim.  
Language English 
Journal/Book name
Japanese: 
English: 
Volume, Number, Page Article No. 25        pp. 1-4
Published date June 25, 2018 
Publisher
Japanese: 
English:ACM 
Conference name
Japanese: 
English:the 8th International Conference on Web Intelligence, Mining and Semantics (WIMS 2018) 
Conference site
Japanese: 
English:Novi Sad 
Official URL https://dl.acm.org/citation.cfm?doid=3227609.3227673
 
DOI https://doi.org/10.1145/3227609.3227673
Abstract Graph embedding aims at learning representations of nodes in a low dimensional vector space. Good embeddings should preserve proximity structure of the original graph and thus are expected to accurately reconstruct the graph. We propose a reconstruction procedure such that the reconstructed graph keeps the total number of weights of the original one. Then we assess the reconstruction precision using a global view based graph similarity metric called DeltaCon. Based on this metric, we found that the embeddings by the state-of-the-art techniques can only preserve part of the proximity structure and is insufficient to achieve high reconstruction accuracy.

©2007 Tokyo Institute of Technology All rights reserved.