However, a comprehensive survey of this emerging topic is still lacking. Therefore, we aim to provide a comprehensive review of directed graph learning, with a particular focus on a data-centric ...

Dir-GNN is a machine learning model that enables learning on directed graphs. This repository contains the official implementation of the paper "Edge Directionality Improves Learning on Heterophilic ...

Abstract: In machine learning applications, the data are often high-dimensional and intrinsically related. It is often of interest finding the underlying structure and the causal relationships of the ...

Abstract: Graph machine learning techniques and notably graph neural networks ... Spectral graph convolutional networks (GCNs), however, seem to encounter shortfalls when it comes to directed graphs.

Methods: We quantified the directed information flow using ... Furthermore, the PDC and graph theory features have been used to discriminate three classes of SAD from HCs using several machine ...