Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge Graphs

Authors

  • Yi Tay Nanyang Technological University
  • Anh Luu Institute for Infocomm Research Singapore
  • Siu Cheung Hui Nanyang Technological University

DOI:

https://doi.org/10.1609/aaai.v31i1.10685

Keywords:

Knowledge Graphs, Representational Learning, Link Prediction

Abstract

Knowledge graphs play a significant role in many intelligent systems such as semantic search and recommendation systems. Recent works in this area of knowledge graph embeddings such as TransE, TransH and TransR have shown extremely competitive and promising results in relational learning. In this paper, we propose a novel extension of the translational embedding model to solve three main problems of the current models. Firstly, translational models are highly sensitive to hyperparameters such as margin and learning rate. Secondly, the translation principle only allows one spot in vector space for each golden triplet. Thus, congestion of entities and relations in vector space may reduce precision. Lastly, the current models are not able to handle dynamic data especially the introduction of new unseen entities/relations or removal of triplets. In this paper, we propose Parallel Universe TransE (puTransE), an adaptable and robust adaptation of the translational model. Our approach non-parametrically estimates the energy score of a triplet from multiple embedding spaces of structurally and semantically aware triplet selection. Our proposed approach is simple, robust and parallelizable. Our experimental results show that our proposed approach outperforms TransE and many other embedding methods for link prediction on knowledge graphs on both public benchmark dataset and a real world dynamic dataset.

Downloads

Published

2017-02-12

How to Cite

Tay, Y., Luu, A., & Hui, S. C. (2017). Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.10685

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning