Complex Sciences. First International Conference, Complex 2009, Shanghai, China, February 23-25, 2009, Revised Papers, Part 2

Research Article

Comparing Networks from a Data Analysis Perspective

Download
491 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-02469-6_67,
        author={Wei Li and Jing-Yu Yang},
        title={Comparing Networks from a Data Analysis Perspective},
        proceedings={Complex Sciences. First International Conference, Complex 2009, Shanghai, China, February 23-25, 2009, Revised Papers, Part 2},
        proceedings_a={COMPLEX PART 2},
        year={2012},
        month={5},
        keywords={network comparison complex networks data analysis graph theory},
        doi={10.1007/978-3-642-02469-6_67}
    }
    
  • Wei Li
    Jing-Yu Yang
    Year: 2012
    Comparing Networks from a Data Analysis Perspective
    COMPLEX PART 2
    Springer
    DOI: 10.1007/978-3-642-02469-6_67
Wei Li1,*, Jing-Yu Yang1,*
  • 1: Nanjing University of Science and Technology
*Contact email: liweinust@gmail.com, yangjy@mail.njust.edu.cn

Abstract

To probe network characteristics, two predominant ways of network comparison are global property statistics and subgraph enumeration. However, they suffer from limited information and exhaustible computing. Here, we present an approach to compare networks from the perspective of data analysis. Initially, the approach projects each node of original network as a high-dimensional data point, and the network is seen as clouds of data points. Then the dispersion information of the principal component analysis (PCA) projection of the generated data clouds can be used to distinguish networks. We applied this node projection method to the yeast protein-protein interaction networks and the Internet Autonomous System networks, two types of networks with several similar higher properties. The method can efficiently distinguish one from the other. The identical result of different datasets from independent sources also indicated that the method is a robust and universal framework.