Link prediction by incidence matrix factorization

Sho Yokoi, Hiroshi Kajino, Hisashi Kashima

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Link prediction suffers from the data sparsity problem. This paper presents and validates our hypothesis that, for sparse networks, incidence matrix factorization (IMF) could perform better than adjacency matrix factorization (AMF), which has been used in many previous studies. A key observation supporting the hypothesis is that IMF models a partially-observed graph more accurately than AMF. A technical challenge for validating our hypothesis is that, unlike AMF approach, there does not exist an obvious method to make predictions using a factorized incidence matrix. To this end, we newly develop an optimization-based link prediction method adopting IMF. We have conducted thorough experiments using synthetic and realworld datasets to investigate the relationship between the sparsity of a network and the performance of the aforementioned two methods. The experimental results show that IMF performs better than AMF as networks become sparser, which strongly validates our hypothesis.

Original languageEnglish
Title of host publicationFrontiers in Artificial Intelligence and Applications
EditorsGal A. Kaminka, Frank Dignum, Eyke Hullermeier, Paolo Bouquet, Virginia Dignum, Maria Fox, Frank van Harmelen
PublisherIOS Press
Number of pages2
ISBN (Electronic)9781614996712
Publication statusPublished - 2016
Event22nd European Conference on Artificial Intelligence, ECAI 2016 - The Hague, Netherlands
Duration: 2016 Aug 292016 Sept 2

Publication series

NameFrontiers in Artificial Intelligence and Applications
ISSN (Print)0922-6389


Conference22nd European Conference on Artificial Intelligence, ECAI 2016
CityThe Hague


Dive into the research topics of 'Link prediction by incidence matrix factorization'. Together they form a unique fingerprint.

Cite this