We propose Adaptive Graph Diffusion Networks (AGDNs) to extend receptive fields of common Message Passing Nueral Networks (MPNNs), without extra layers (feature transformations) or decoupling model ...

Graph Diffusion Network (GDN) is a framework that combines a graph neural network with a diffusion model to learn a differentiable surrogate of an ABM, from ABM-generated data. In this framework, a ...

Keywords: brain network, beta-informativeness-diffusion, graph embedding, schizophrenia, bipolar disorder. Citation: Huang Y, Li Y, Yuan Y, Zhang X, Yan W, Li T, Niu Y, Xu M, Yan T, Li X, Li D, Xiang ...

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 based GNNs, e.g., ...

Partial Differential Equation (PDE) based diffusion has been utilized for image denoising for more than two decades. It is known that the process of diffusion preserves the edges and object boundaries ...

Text classification is a critical task for understanding the knowledge behind text, especially in medical text. In this paper, we propose a medical graph diffusion model, named the MGD model, for the ...

Understanding and predicting interface diffusion phenomena in materials is crucial for various industrial applications, including semiconductor manufacturing, battery technology, and catalysis. In ...