INK: knowledge graph embeddings for node classification

Deep learning techniques are increasingly being applied to solve various machine learning tasks that use Knowledge Graphs as input data. However, these techniques typically learn a latent representation for the entities of interest internally, which is then used to make decisions. This latent representation is often not comprehensible to humans, which is why deep learning techniques are often considered to be black boxes. In this paper, we present INK: Instance Neighbouring by using Knowledge, a novel technique to learn binary feature-based representations, which are comprehensible to humans, for nodes of interest in a knowledge graph. We demonstrate the predictive power of the node representations obtained through INK by feeding them to classical machine learning techniques and comparing their predictive performances for the node classification task to the current state of the art: Graph Convolutional Networks (R-GCN) and RDF2Vec. We perform this comparison both on benchmark datasets and using a real-world use case.

Automated summary

This paper presents a novel technique called INK, which learns binary feature-based representations for nodes in a knowledge graph that are comprehensible to humans. By comparing the predictive performances of the node representations obtained through INK with state-of-the-art techniques, such as Graph Convolutional Networks (R-GCN) and RDF2Vec, on both benchmark datasets and a real-world use case, the predictive power of INK is demonstrated.