.png){kind=icon}
Return
Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes
.png){kind=icon}
OA
AI
DOI：10.24963/ijcai.2021/395.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Journal
No journal information available
Organization
No organization information available
Cited Papers
No cited papers available