Marine: Multi-relational network embeddings with relational proximity and node attributes
Journal
The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
Pages
470-479
Date Issued
2019
Author(s)
Abstract
Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE. © 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.
SDGs
Other Subjects
Classification (of information); Marine applications; World Wide Web; Homogeneous network; Knowledge graphs; Large-scale network; Multi label classification; Multi-relational networks; Real-world networks; Relation information; Vector transformation; Embeddings
Type
conference paper