Auto-encoding a Knowledge Graph Using a Deep Belief Network: A Random Fields Perspective

TL;DR

This paper presents a method for encoding a knowledge graph into a hierarchical representation using a deep belief network, capturing the structure and distribution of the data efficiently.

Contribution

It introduces a novel approach combining knowledge graphs with deep belief networks from a random fields perspective, enabling hierarchical encoding and distribution modeling.

Findings

Hierarchical representations of knowledge graphs can be effectively derived.

Energy-based neural networks capture the structure of the knowledge graph.

Efficient output of the underlying equilibrium distribution is demonstrated.

Abstract

We started with a knowledge graph of connected entities and descriptive properties of those entities, from which, a hierarchical representation of the knowledge graph is derived. Using a graphical, energy-based neural network, we are able to show that the structure of the hierarchy can be internally captured by the neural network, which allows for efficient output of the underlying equilibrium distribution from which the data are drawn.