On multi-relational link prediction with bilinear models

Wang, Yanjie ; Gemulla, Rainer ; Li, Hui

Vorschau

PDF
On Multi-Relational Link Prediction with Bilinear Models.pdf - Veröffentlichte Version
Download (287kB)

URL:	https://madoc.bib.uni-mannheim.de/44074
Weitere URL:	https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/v...
URN:	urn:nbn:de:bsz:180-madoc-440741
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2018
Buchtitel:	The Thirty-Second AAAI Conference on Artificial Intelligence, The Thirtieth Innovative Applications of Artificial Intelligence Conference, The Eighth AAAI Symposium on Educational Advances in Artificial Intelligence : New Orleans, Louisiana USA
Seitenbereich:	4227-4234
Veranstaltungstitel:	AAI-18: Thirty-Second AAAI Conference on Artificial Intelligence
Veranstaltungsort:	New Orleans, LA
Veranstaltungsdatum:	February 2-7, 2018
Ort der Veröffentlichung:	Palo Alto, CA
Verlag:	AAAI Press
ISBN:	978-1-57735-800-8
ISSN:	2374-3468
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Practical Computer Science I: Data Analytics (Gemulla 2014-)
Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	004 Informatik
Freie Schlagwörter (Englisch):	Relational Learning ; Embedding Learning ; Knowledge Graph
Abstract:	We study bilinear embedding models for the task of multi-relational link prediction and knowledge graph completion. Bilinear models belong to the most basic models for this task, they are comparably efficient to train and use, and they can provide good prediction performance. The main goal of this paper is to explore the expressiveness of and the connections between various bilinear models proposed in the literature. In particular, a substantial number of models can be represented as bilinear models with certain additional constraints enforced on the embeddings. We explore whether or not these constraints lead to universal models, which can in principle represent every set of relations, and whether or not there are subsumption relationships between various models. We report results of an independent experimental study that evaluates recent bilinear models in a common experimental setup. Finally, we provide evidence that relation-level ensembles of multiple bilinear models can achieve state-of-the-art prediction performance.