Finding Novel Links in COVID-19 Knowledge Graph Using Graph Embedding Techniques
Published in Smoky Mountains Computational Sciences and Engineering Conference, 2021
With the explosion of scientific literature, automated tools are essential for efficient knowledge discovery. This study analyzes a COVID-19 knowledge graph and applies graph embedding and machine learning to predict undiscovered links between concepts. Among the tested methods, SDNE with a neural network achieved the highest accuracy (F1-score: 88.0%), followed by GraphSAGE (86.3%). Predictions were ranked using PageRank product, offering insights into biomedical research connections.
Recommended citation: Patel, A., et al. Finding Novel Links in COVID-19 Knowledge Graph Using Graph Embedding Techniques. In Smoky Mountains Computational Sciences and Engineering Conference (pp. 430-441). Cham: Springer International Publishing
Download Paper