Simple jQuery Dropdowns
Please use this identifier to cite or link to this item:
Title: A general view for network embedding as matrix factorization
Authors: Xin Liu
Tsuyoshi Murata
Kyoung Sook Kim
Chatchawan Kotarasu
Chenyi Zhuang
Tokyo Institute of Technology
Mahidol University
National Institute of Advanced Industrial Science and Technology
Keywords: Computer Science
Issue Date: 30-Jan-2019
Citation: WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. (2019), 375-383
Abstract: © 2019 Association for Computing Machinery. We propose a general view that demonstrates the relationship between network embedding approaches and matrix factorization. Unlike previous works that present the equivalence for the approaches from a skip-gram model perspective, we provide a more fundamental connection from an optimization (objective function) perspective. We demonstrate that matrix factorization is equivalent to optimizing two objectives: one is for bringing together the embeddings of similar nodes; the other is for separating the embeddings of distant nodes. The matrix to be factorized has a general form: S−β·1. The elements of S indicate pairwise node similarities. They can be based on any user-defined similarity/distance measure or learned from random walks on networks. The shift number β is related to a parameter that balances the two objectives. More importantly, the resulting embeddings are sensitive to β and we can improve the embeddings by tuning β. Experiments show that matrix factorization based on a new proposed similarity measure and β-tuning strategy significantly outperforms existing matrix factorization approaches on a range of benchmark networks.
Appears in Collections:Scopus 2019

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.