Knowledge Representation in Graphs using Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based approach for embedding and visualizing knowledge graphs, improving graph completion and insight extraction, especially in biomedical data with sparse and complex relationships.

Contribution

It presents a novel combination of CNNs and Self-Organised Maps for embedding, visualizing, and completing knowledge graphs in biomedical domains.

Findings

Performance comparable to structural models in biomedical graph completion

Effective visualization of complex biomedical interactions

Enhanced insights from sparse knowledge graphs

Abstract

Knowledge Graphs (KG) constitute a flexible representation of complex relationships between entities particularly useful for biomedical data. These KG, however, are very sparse with many missing edges (facts) and the visualisation of the mesh of interactions nontrivial. Here we apply a compositional model to embed nodes and relationships into a vectorised semantic space to perform graph completion. A visualisation tool based on Convolutional Neural Networks and Self-Organised Maps (SOM) is proposed to extract high-level insights from the KG. We apply this technique to a subset of CTD, containing interactions of compounds with human genes / proteins and show that the performance is comparable to the one obtained by structural models.