Node2vec and arXiv data

Since its publication in 2016 by Aditya Grover and Jure Leskovec, Node2vec has become the go-to algorithm to easily compute embeddings for nodes in a graph/network. Working with embeddings has […]

Knowledge Graph Features and Explanation

Although latent feature models such as TransE are demonstrating state-of-the-art performance in the task of link prediction in knowledge graphs, they act as a black box. Latent feature models rely […]

Translating Embeddings (TransE)

In this post I present Translating Embeddings (TransE), a method for the prediction of missing relationships in knowledge graphs. Rather than digging into the mathematics, I focus on presenting the […]