Home > Papers

 
 
Bidirectional Group Random Walk Based Network Embedding for Asymmetric Proximity
Shen Jia-Wei 1,Shu Xin-Cheng 2,Yang Hu 1 *,Yang Hu 1 *
1.College of Mathematics and Statistics, Chongqing University, Chongqing 401331
2.Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023
*Correspondence author
#Submitted by
Subject:
Funding: National Natural Science Foundation of China （No.11671059）, graduate scientific research and innovation foundation of Chongqing China （No.CYS20041）
Opened online: 2 April 2022
Accepted by: none
Citation: Shen Jia-Wei,Shu Xin-Cheng,Yang Hu.Bidirectional Group Random Walk Based Network Embedding for Asymmetric Proximity[OL]. [ 2 April 2022] http://en.paper.edu.cn/en_releasepaper/content/4756843
 
 
Network embedding aims to represent a network into a low dimensional space where the network structural information and inherent properties are maximumly preserved. Random walk based network embedding methods such as DeepWalk and node2vec have shown outstanding performance in the aspect of preserving the network topological structure. However, these approaches either predict the distribution of a node's neighbors in both direction together, which makes them unable to capture any asymmetric relationship in a network; or preserve asymmetric relationship in only one direction and hence lose the one in another direction. To address these limitations, this paper proposes bidirectional group random walk based network embedding method (BiGRW), which treats the distributions of a node's neighbors in the forward and backward direction in random walks as two different asymmetric network structural information. The basic idea of BiGRW is to learn a representation for each node that is useful to predict its distribution of neighbors in the forward and backward direction separately. Apart from that, a novel random walk sampling strategy is proposed with a parameter $\alpha$ to flexibly control the trade-off between breadth-first sampling (BFS) and depth-first sampling (DFS). To learn representations from node attributes, we design an attributed version of BiGRW (BiGRW-AT). Experimental results on several benchmark datasets demonstrate that the proposed methods significantly outperform the state-of-the-art plain and attributed network embedding methods on tasks of node classification and clustering.
Keywords:Network embedding, Random walk, Network structure, Node attribute
 
 
 

For this paper
  • ● PDF (0B)
  • ● Revision 0 　　
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags
Add yours

Related Papers
  • Other similar papers

Statistics
PDF Downloaded 5
Bookmarked 0
Recommend 0
Comments Array
Submit your papers