We propose a novel class of graph neural networks based on the discretized Beltrami flow, a
non-Euclidean diffusion PDE. In our model, node features are supplemented with positional …

Abstract We present Graph Neural Diffusion (GRAND) that approaches deep learning on
graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as …

ABSTRACT We propose GRAph Neural Diffusion with a source term (GRAND++) for graph
deep learning with a limited number of labeled nodes, ie, low-labeling rate. GRAND++ is a …

The success of graph neural networks (GNNs) largely relies on the process of aggregating
information from neighbors defined by the input graph structures. Notably, message passing …

This paper builds on the connection between graph neural networks and traditional
dynamical systems. We propose continuous graph neural networks (CGNN), which …

Graph neural networks (GNNs) extends the functionality of traditional neural networks to
graph-structured data. Similar to CNNs, an optimized design of graph convolution and …

Abstract Current Graph Neural Networks (GNN) architectures generally rely on two important
components: node features embedding through message passing, and aggregation with a …

Graph neural networks (GNNs) have shown promising results across various graph learning
tasks, but they often assume homophily, which can result in poor performance on …

Graph convolution is the core of most Graph Neural Networks (GNNs) and usually
approximated by message passing between direct (one-hop) neighbors. In this work, we …

Due to the over-smoothing issue, most existing graph neural networks can only capture
limited dependencies with their inherently finite aggregation layers. To overcome this …