Knowledge Graph Embeddings

Author(s): Edward Ma

Originally published on Towards AI.

Photo by chuttersnap on Unsplash

In the previous stories, we introduced Introduction to Graph Embeddings, Random Walk in Node Embeddings, 4 Graph Neural Networks, and When GraphSAGE meets Pinterest.

In this article, I introduce TRESCAL, HolE, and SimplE, which are applying in knowledge graph embeddings. Both TRESCAL and HolE are enhanced versions of RESCAL. The authors used different approaches to overcome the limitation of RESCAL.

TRESCAL (Chang et al., 2014) is an enhanced version of RESCAL(Nickle et al., 2011). Authors consider the type of entity and relation to removing unnecessary computation such that less training time is required, and model accuracy can be… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI