GRAPH NEURAL REACTION DIFFUSION MODELS

Moshe Eliasof

doi:10.1137/23M1576700

GRAPH NEURAL REACTION DIFFUSION MODELS

2024-08-01

0

OA

AI

DOI：10.1137/23M1576700

Original

Original request for help

Save

Abstract

En 中文

The integration of graph neural networks (GNNs) and neural ordinary and partial differential equations has been extensively studied in recent years. GNN architectures powered by neural differential equations allow us to reason about their behavior, and develop GNNs with desired properties such as controlled smoothing or energy conservation. In this paper we take inspiration from Turing instabilities in a reaction diffusion (RD) system of partial differential equations, and propose a novel family of GNNs based on neural RD systems, called RDGNN. We show that our RDGNN is powerful for the modeling of various data types, from homophilic, to heterophilic, and spatiotemporal datasets. We discuss the theoretical properties of our RDGNN, its implementation, and show that it improves or offers competitive performance to state-of-the-art methods.

Keywords:

graph neural networks

reaction diffusion

Turing patterns

GRAPH NEURAL REACTION DIFFUSION MODELS

Abstract

Journal

Organization