2.3 GCATCMDA Figure 1 illustrates the workflow of GCATCMDA, a model based on graph neural networks and contrastive learning for predicting effective candidate sets of microbe-disease associations.

Graph contrastive learning, as a strategy within self-supervised learning, revolves around the core idea of driving graph representation learning by understanding the similarity between different ...

Impact Statement: In this article, to capture higher-order structural information of the heterogeneous graphs, we proposed AHGCL which introduces a novel data augmentation method by calculating cosine ...

Transformers, having the superior ability to capture both adjacent and long-range dependencies, have been applied to the graph representation learning field. Existing methods are permanently ...

Supervised Contrastive Learning. While unsupervised contrastive learning has shown significant improvements, it overlooks the usefulness of available user-bundle interactions when dealing with ...