Embedding Mapping Approaches for Tensor Factorization and Knowledge Graph Modelling

Yang, Yinchong; Esteban, Cristóbal and Tresp, Volker (2016): Embedding Mapping Approaches for Tensor Factorization and Knowledge Graph Modelling. In: Sack, Harald (ed.) : The Semantic Web. Latest Advances and New Domains 13th International Conference, ESWC 2016, Heraklion, Crete, Greece, May 29 - June 2, 2016, Proceedings. Theoretical Computer Science and General Issues, Vol. 9678. Cham: Springer. pp. 199-213

Abstract

Latent embedding models are the basis of state-of-the art statistical solutions for modelling Knowledge Graphs and Recommender Systems. However, to be able to perform predictions for new entities and relation types, such models have to be retrained completely to derive the new latent embeddings. This could be a potential limitation when fast predictions for new entities and relation types are required. In this paper we propose approaches that can map new entities and new relation types into the existing latent embedding space without the need for retraining. Our proposed models are based on the observable - even incomplete-features of a new entity, e.g. a subset of observed links to other known entities. We show that these mapping approaches are efficient and are applicable to a wide variety of existing factorization models, including nonlinear models. We report performance results on multiple real-world datasets and evaluate the performances from different aspects.

• Item Type: Book Section
• Faculties: Mathematics, Computer Science and Statistics > Computer Science
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• ISBN: 978-3-319-34128-6; 978-3-319-34129-3
• Place of Publication: Cham
• Language: English