LINE: Large-Scale Information Network Embedding
Year: 2024
Type: dataset
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 em-bedding 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 informa-tion 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 in-ference. 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 ma-chine. The source code of the LINE is available online.1
Source: TIB Data Manager
DOI: 10.57702/6e6l3h4g
Author: Tang, Jian
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6936242187
