In this survey, we provide a thorough examination of the current landscape and future prospects of data-centric directed graph machine learning, ofering an in-depth review of recent advancements in graph …

In this paper, we introduce MagNet, a graph convolutional neural network for directed graphs based on the magnetic Laplacian. Most graph neural networks fall into one of two families, spectral networks or …

Using this Laplacian, we propose a general framework, called Continuous Edge Direction (CoED) GNN, for learning on graphs with fuzzy edges and prove its expressivity limits using a generalization of the …

Jan 1, 2020 · In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open …

In this paper, we propose MagNet, a GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian. This matrix encodes undirected geometric structure in the …

In our paper, we show that in heterophilic settings, treating the graph as directed increases the effective homophily of the graph, suggesting a potential gain from the correct use of directionality information.

in gene regulatory networks, web connectivity graphs, and power grids. We demonstrate through extensive experiments on both synthetic and real graph ensemble datasets that learning continuous …

Understanding the differences between Directed Graphs (Digraphs) and Undirected Graphs is crucial for choosing the right graph representation for a given problem. In this article, we’ll explore their …

Aug 30, 2024 · In this tutorial, we’ll study the differences between directed and undirected graphs. We’ll also learn what are the cases in which we should prefer using one over the other. At first, we’ll …

Graph machine-learning (ML) methods have recently attracted great attention and have made significant progress in graph applications. To date, most graph ML approaches have been evaluated on...