Papers › Graph Neural Reaction Diffusion Models

Graph Neural Reaction Diffusion Models

16 Jun 2024arXiv:2406.10871archive 2025-07-28

Moshe Eliasof, Eldad Haber, Eran Treister

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Node Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor RDGNN-I Accuracy 38.69 ± 1.41 #6 of 62 Archive leaderboard report
Node Classification Chameleon RDGNN-I Accuracy 74.79 ± 2.14 #11 of 61 Archive leaderboard report
Node Classification Cornell RDGNN-I Accuracy 92.72 ± 5.88 #1 of 60 Archive leaderboard report
Node Classification Squirrel RDGNN-I Accuracy 65.62 ± 2.33 #16 of 59 Archive leaderboard report
Node Classification Texas RDGNN-S Accuracy 94.59 ± 5.97 #1 of 62 Archive leaderboard report
Node Classification Texas RDGNN-I Accuracy 93.51 ± 5.93 #2 of 62 Archive leaderboard report
Node Classification Wisconsin RDGNN-I Accuracy 93.72 ± 4.59 #2 of 63 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections