Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes
This addresses a limitation in knowledge graph embeddings for domains like genetics and social networks, but it is incremental as it builds on existing architectures.
The authors tackled the problem of knowledge graph embedding models not capturing numeric edge attributes, which represent uncertainty or importance, by proposing a method that injects these attributes into the scoring layer, resulting in improved predictive power over baselines and the UKGE model.
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.