Computer scientists at the University of Southern California (USC) considered which knowledge graph (KG) representations are best for different applications.
The researchers focused on the performance of four types of KG representations across three use-cases: exploring knowledge, writing queries, and building machine learning models.
Said USC's Jay Pujara, "Basically, there was not a clear winner. This is not a situation where you can say a certain type of representation is always best for a certain type of task."
However, the researchers found that one type of representation, Qualifiers, works well in all scenarios. This method assigns information to the edges connecting the entities to present additional facts.
Pujara noted, "There's still a case where each of these proposed representations might have some benefit."
From USC Viterbi School of Engineering
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found