Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction
This work addresses a scalability bottleneck for graph neural networks in biomedical applications, offering an incremental improvement over existing sampling techniques.
The paper tackled the problem of scaling graph neural networks to large multi-relational graphs by proposing a relation-dependent sampling method that learns to balance relation-type probabilities based on frequency and importance, resulting in improved accuracy and efficiency in drug-drug interaction prediction.
Sampling is an established technique to scale graph neural networks to large graphs. Current approaches however assume the graphs to be homogeneous in terms of relations and ignore relation types, critically important in biomedical graphs. Multi-relational graphs contain various types of relations that usually come with variable frequency and have different importance for the problem at hand. We propose an approach to modeling the importance of relation types for neighborhood sampling in graph neural networks and show that we can learn the right balance: relation-type probabilities that reflect both frequency and importance. Our experiments on drug-drug interaction prediction show that state-of-the-art graph neural networks profit from relation-dependent sampling in terms of both accuracy and efficiency.