Information Flow in Graph Neural Networks: A Clinical Triage Use Case
This work addresses a specific bottleneck in GNN training for clinical triage applications, offering incremental improvements in link prediction performance.
The paper tackled the challenge of efficient GNN training by investigating how embedding information flow affects link prediction in knowledge graphs, proposing a model that decouples GNN connectivity from graph data connectivity and showing that incorporating domain knowledge into connectivity improves performance, with negative edges being crucial and too many layers degrading results.
Graph Neural Networks (GNNs) have gained popularity in healthcare and other domains due to their ability to process multi-modal and multi-relational graphs. However, efficient training of GNNs remains challenging, with several open research questions. In this paper, we investigate how the flow of embedding information within GNNs affects the prediction of links in Knowledge Graphs (KGs). Specifically, we propose a mathematical model that decouples the GNN connectivity from the connectivity of the graph data and evaluate the performance of GNNs in a clinical triage use case. Our results demonstrate that incorporating domain knowledge into the GNN connectivity leads to better performance than using the same connectivity as the KG or allowing unconstrained embedding propagation. Moreover, we show that negative edges play a crucial role in achieving good predictions, and that using too many GNN layers can degrade performance.