Nature

Unifying topological structure and self-attention mechanism for node classification in directed networks

Graph data is essential for modeling complex relationships among entities. Graph Neural Networks (GNNs) have demonstrated effectiveness in processing low-order undirected graph data; however, in ...
Nature

Causality-aware graph neural networks for functional stratification and phenotype prediction at scale

The sparsity of causal interpretation in medical sciences 1,2,3 and the need to utilize it using high-throughput genomic and transcriptomic data, combined with the wider availability of computational ...