Auto-encoding a Knowledge Graph Using a Deep Belief Network: A Random Fields Perspective
This addresses knowledge graph representation for AI applications, but appears incremental as it applies existing neural network methods to this domain.
The researchers tackled the problem of representing knowledge graphs by developing a deep belief network that captures hierarchical structure, demonstrating it can efficiently output the underlying equilibrium distribution of the data.
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.