Graph Neural Reaction Diffusion Models
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. We \textcolor{black}{demonstrate} that our RDGNN is powerful for the modeling of various data types, from homophilic, to heterophilic, and spatio-temporal 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Node ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GREAD: Graph Neural Reaction-Diffusion Networks
Graph neural networks (GNNs) are one of the most popular research topics for deep learning. GNN methods typically have been designed on top of the graph signal processing theory. In particular, diffusion equations have b…
Node ClassificationRDGCL: Reaction-Diffusion Graph Contrastive Learning for Recommendation
Contrastive learning (CL) has emerged as a promising technique for improving recommender systems, addressing the challenge of data sparsity by using self-supervised signals from raw data. Integration of CL with graph con…
Contrastive LearningData IntegrationDiversityRecommendation SystemsFrom Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks
Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-way feature mixing. This work investigate…
Feature Transportation Improves Graph Neural Networks
Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In …
Node ClassificationMulti-grid reaction-diffusion master equation: applications to morphogen gradient modelling
The multi-grid reaction-diffusion master equation (mgRDME) provides a generalization of stochastic compartment-based reaction-diffusion modelling described by the standard reaction-diffusion master equation (RDME). By en…