LINE
Top Cited Papers
- 18 May 2015
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1067-1077
- https://doi.org/10.1145/2736277.2741093
Abstract
This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the "LINE," which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online.Comment: WWW 201Keywords
Funding Information
- National Science Foundation (IIS-1054199, CCF-1048168)
- National Natural Science Foundation of China (61472006)
This publication has 13 references indexed in Scilit:
- Reducing the sampling complexity of topic modelsPublished by Association for Computing Machinery (ACM) ,2014
- DeepWalkPublished by Association for Computing Machinery (ACM) ,2014
- Information network or social network?Published by Association for Computing Machinery (ACM) ,2014
- Distributed large-scale natural graph factorizationPublished by Association for Computing Machinery (ACM) ,2013
- Node Classification in Social NetworksPublished by Springer Science and Business Media LLC ,2011
- Introduction to Information RetrievalPublished by Cambridge University Press (CUP) ,2008
- The link‐prediction problem for social networksJournal of the American Society for Information Science and Technology, 2007
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- Multidimensional ScalingPublished by Taylor & Francis Ltd ,2000
- The Strength of Weak TiesAmerican Journal of Sociology, 1973