Proceedings

Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes

Sumit Pai, Luca Costabello

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2869-2875.

https://doi.org/10.24963/ijcai.2021/395

Keywords

  • Machine Learning: Relational Learning
  • Natural Language Processing: Embeddings

Abstract

Numeric values associated to edges of a knowledge graph have been used to represent uncertainty, edge importance, and even out-of-band knowledge in a growing number of scenarios, ranging from genetic data to social networks. Nevertheless, traditional knowledge graph embedding models are not designed to capture such information, to the detriment of predictive power.

We propose a novel method that injects numeric edge attributes into the scoring layer of a traditional knowledge graph embedding architecture. Experiments with publicly available numeric-enriched knowledge graphs show that our method outperforms traditional numeric-unaware baselines as well as the recent UKGE model.

Sumit Pai, and Luca Costabello. 2021. Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2869–2875. https://doi.org/10.24963/ijcai.2021/395
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards