Information Flow in Graph Neural Networks: A Clinical Triage Use Case

TL;DR

This paper explores how information flow within Graph Neural Networks impacts link prediction in Knowledge Graphs, emphasizing the importance of domain knowledge, negative edges, and layer depth for improved clinical triage outcomes.

Contribution

It introduces a mathematical model decoupling GNN connectivity from data graph connectivity and evaluates the impact of domain knowledge and negative edges on GNN performance.

Findings

Incorporating domain knowledge improves GNN link prediction accuracy.

Negative edges are crucial for effective GNN training.

Too many GNN layers can reduce prediction performance.

Abstract

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.