Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024.

Moshe Eliasof, Eldad Haber, Eran Treister

Abstract

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 blackdemonstrate 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.

Benchmark Results

Tested on 8 datasets 32 baseline values reported too low

Tables show presented results in global context (best 3 papers + GCN + MLP).

Classic

Cora

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	GraphSAGE+CNA code ↗ GNN global	0.9418 ±0.0033	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
2	GCN+CNA code ↗ GNN global	0.9366 ±0.0048	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
3	TransformerConv code ↗ GNN global	0.9350 ±0.0058	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
21	GCN GNN baseline actual #21 vs paper #195 174 places worse	0.9004 best reported	actual #21 vs paper #195 174 places worse paper 0.8577 ±0.0127 best at pub: Understanding Heterophily for Graph Neural Networks (ICML 2024) paper 0.8577 ±0.0127 Δ at pub 0.0427
22	RDGNN-I Hyb ★ proposed	0.8991 ±0.0110	This paper
29	RDGNN-S GNN ★ proposed	0.8953 ±0.0122	This paper
39	SAGE GNN global	0.8911 ±0.0012	Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
44	GAT GNN baseline actual #44 vs paper #175 131 places worse	0.8897 ±0.0014 best reported	actual #44 vs paper #175 131 places worse paper 0.8637 ±0.0048 best at pub: Learned Low Precision Graph Neural Networks (2020) best today: Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models (2025) paper 0.8637 ±0.0048 Δ at pub 0.0253 Δ today 0.0260
45	GCNII GNN baseline actual #45 vs paper #66 21 places worse	0.8893 ±0.0137 best reported	actual #45 vs paper #66 21 places worse paper 0.8849 ±0.0125 best at pub: Language is All a Graph Needs (2023) best today: Large Language Model Meets Graph Neural Network in Knowledge Distillation (AAAI 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8849 ±0.0125 Δ at pub 0.0044 Δ today 0.0044
51	H2GCN GNN baseline actual #51 vs paper #107 56 places worse	0.8882 ±0.0011 best reported	actual #51 vs paper #107 56 places worse paper 0.8787 ±0.0120 best at pub: Feature Transportation Improves Graph Neural Networks (AAAI 2023) best today: Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.8787 ±0.0120 Δ today 0.0095
59	PDE-GCNM GNN baseline	0.8860	This paper
62	GREAD GNN baseline	0.8857 ±0.0066	This paper
79	ACMII-GCN GNN baseline	0.8825 ±0.0096	This paper
82	WRGAT GNN baseline	0.8820 ±0.0226	This paper
96	GRAFF GNN baseline	0.8801 ±0.0103	This paper
103	GGCN GNN baseline	0.8795 ±0.0105	This paper
113	MixHop GNN baseline	0.8761 ±0.0203	This paper
138	NSD GNN baseline	0.8714 ±0.0113	This paper
168	DMP GNN baseline	0.8652	This paper
207	Geom-GCN GNN baseline actual #207 vs paper #214 7 places worse	0.8540 ±0.0040 best reported	actual #207 vs paper #214 7 places worse paper 0.8527 ±0.0157 best at pub: The Expressive Power of Graph Neural Networks: A Survey (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.8527 ±0.0157 Δ at pub 0.0013
243	LINKX GNN baseline	0.8464 ±0.0113	This paper
724	MLP Trad global	0.7768	Understanding Heterophily for Graph Neural Networks

CiteSeer

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	CNA code ↗ GNN global	0.9575 ±0.0058	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
2	IS-GIB code ↗ Hyb global	0.9390 ±0.0187	Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization code ↗
3	EERM code ↗ GNN global	0.9112 ±0.0145	Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization code ↗
35	GAT GNN baseline actual #35 vs paper #209 174 places worse	0.8080 ±0.0026 best reported	actual #35 vs paper #209 174 places worse paper 0.7432 ±0.0123 best at pub: Feature Expansion for Graph Neural Networks (ICML 2023) paper 0.7432 ±0.0123 Δ at pub 0.0648
36	GCNII GNN baseline actual #36 vs paper #108 72 places worse	0.8076 ±0.0030 best reported	actual #36 vs paper #108 72 places worse paper 0.7713 ±0.0148 best at pub: Feature Expansion for Graph Neural Networks (ICML 2023) paper 0.7713 ±0.0148 Δ at pub 0.0363
44	GCN GNN baseline actual #44 vs paper #257 213 places worse	0.8033 ±0.0088 best reported	actual #44 vs paper #257 213 places worse paper 0.7368 ±0.0136 best at pub: Gophormer: Ego-Graph Transformer for Node Classification (2021) best today: NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification (2024) paper 0.7368 ±0.0136 Δ at pub 0.0575 Δ today 0.0665
61	GraphSAGE GNN global	0.7923 ±0.0053	Gophormer: Ego-Graph Transformer for Node Classification
80	PDE-GCNM GNN baseline	0.7848	This paper
84	RDGNN-I Hyb ★ proposed	0.7834 ±0.0155	This paper
88	Geom-GCN GNN baseline	0.7799 ±0.0115	This paper
94	RDGNN-S GNN ★ proposed	0.7782 ±0.0148	This paper
99	GREAD GNN baseline	0.7760 ±0.0181	This paper
104	GRAFF GNN baseline	0.7730 ±0.0185	This paper
107	NSD GNN baseline	0.7714 ±0.0157	This paper
108	GGCN GNN baseline	0.7714 ±0.0145	This paper
110	ACMII-GCN GNN baseline	0.7712 ±0.0158	This paper
111	H2GCN GNN baseline	0.7711 ±0.0157	This paper
117	DMP GNN baseline	0.7687	This paper
119	WRGAT GNN baseline	0.7681 ±0.0189	This paper
126	MixHop GNN baseline	0.7626 ±0.0295	This paper
312	LINKX GNN baseline	0.7319 ±0.0099	This paper
350	MLP code ↗ Trad global	0.7289 ±0.0010	Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax code ↗

PubMed

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	LGTL GT global	0.9518 ±0.0011	Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models
2	MixHop (LO) code ↗ GNN global	0.9513 ±0.0038	LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework code ↗
3	GraphSAGE (LO) code ↗ GNN global	0.9511 ±0.0036	LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework code ↗
16	H2GCN GNN baseline actual #16 vs paper #87 71 places worse	0.9361 ±0.0013 best reported	actual #16 vs paper #87 71 places worse paper 0.8949 ±0.0038 best at pub: Optimization-Induced Graph Implicit Nonlinear Diffusion (ICML 2022) best today: Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models (2025) paper 0.8949 ±0.0038 Δ today 0.0412
18	GCN GNN baseline actual #18 vs paper #156 138 places worse	0.9296 ±0.0015 best reported	actual #18 vs paper #156 138 places worse paper 0.8813 ±0.0050 best at pub: Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning (ICLR 2024) best today: Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models (2025) paper 0.8813 ±0.0050 Δ at pub 0.0191 Δ today 0.0483
20	GAT GNN baseline actual #20 vs paper #180 160 places worse	0.9233 ±0.0018 best reported	actual #20 vs paper #180 160 places worse paper 0.8762 ±0.0110 best at pub: Tackling Over-Smoothing for General Graph Convolutional Networks (2020) best today: Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models (2025) paper 0.8762 ±0.0110 Δ at pub 0.0208 Δ today 0.0471
55	RDGNN-I Hyb ★ proposed	0.9037 ±0.0043	This paper
58	GCNII GNN baseline	0.9030 ±0.0043	This paper
62	GREAD GNN baseline	0.9023 ±0.0055	This paper
66	RDGNN-S GNN ★ proposed	0.9011 ±0.0062	This paper
69	Geom-GCN GNN baseline	0.9005 ±0.0047	This paper
70	MixHop GNN baseline actual #70 vs paper #247 177 places worse	0.9004 ±0.0141 best reported	actual #70 vs paper #247 177 places worse paper 0.8531 ±0.0229 best at pub: Language is All a Graph Needs (2023) paper 0.8531 ±0.0229 Δ at pub 0.0473
71	GRAFF GNN baseline	0.9004 ±0.0041	This paper
75	PDE-GCNM GNN baseline	0.8993	This paper
83	ACMII-GCN GNN baseline	0.8971 ±0.0048	This paper
88	NSD GNN baseline	0.8949 ±0.0040	This paper
96	DMP GNN baseline	0.8927	This paper
98	GGCN GNN baseline	0.8915 ±0.0037	This paper
116	SAGE GNN global	0.8881 ±0.0015	Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
129	WRGAT GNN baseline	0.8852 ±0.0092	This paper
162	LINKX GNN baseline	0.8786 ±0.0077	This paper
210	MLP code ↗ Trad global	0.8690 ±0.0074	On the Equivalence of Graph Convolution and Mixup code ↗

Heterophilic Graphs

Texas

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	P^2GNN Hyb global	0.9672 ±0.0147	$P^2$GNN: Two Prototype Sets to boost GNN Performance
2	DoG code ↗ ext data GNN global	0.9660 ±0.0210	Diffusion on Graph: Augmentation of Graph Structure for Node Classification code ↗
3	GPF-plus code ↗ ext data GNN global	0.9583 ±0.0419	ProG: A Graph Prompt Learning Benchmark code ↗
9	RDGNN-S GNN ★ proposed	0.9459 ±0.0597	This paper
19	RDGNN-I Hyb ★ proposed	0.9351 ±0.0593	This paper
24	PDE-GCNM GNN baseline	0.9324	This paper
28	GPRGNN GNN baseline actual #28 vs paper #269 241 places worse	0.9295 ±0.0131 best reported	actual #28 vs paper #269 241 places worse paper 0.7838 ±0.0436 best at pub: Node-oriented Spectral Filtering for Graph Neural Networks (2022) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.7838 ±0.0436 Δ at pub 0.1454 Δ today 0.1457
34	MLP Trad global	0.9230 ±0.0070	Design your own universe: a physics-informed agnostic method for enhancing graph neural networks
39	GGCN GNN baseline actual #39 vs paper #148 109 places worse	0.9213 ±0.0305 best reported	actual #39 vs paper #148 109 places worse paper 0.8486 ±0.0455 best at pub: Global-Local Graph Neural Networks for Node-Classification (2024) best today: Graph Wave Networks (WWW 2025) paper 0.8486 ±0.0455 Δ at pub 0.0200 Δ today 0.0727
40	H2GCN GNN baseline actual #40 vs paper #148 108 places worse	0.9189 ±0.0393 best reported	actual #40 vs paper #148 108 places worse paper 0.8486 ±0.0723 best at pub: Global-Local Graph Neural Networks for Node-Classification (2024) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8486 ±0.0723 Δ at pub 0.0279 Δ today 0.0703
53	GraphSAGE code ↗ GNN global	0.9000 ±0.0365	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
57	GREAD GNN baseline actual #57 vs paper #57	0.8973 ±0.0449	actual #57 vs paper #57 paper 0.8973 ±0.0449 prev best: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory (KDD 2024) Improvement within reported uncertainty; not highlighted. paper 0.8973 ±0.0449 Δ at pub 0.0514
61	FAGCN GNN baseline actual #61 vs paper #193 132 places worse	0.8961 ±0.0152 best reported	actual #61 vs paper #193 132 places worse paper 0.8243 ±0.0287 best at pub: Node-oriented Spectral Filtering for Graph Neural Networks (2022) paper 0.8243 ±0.0287 Δ at pub 0.0718
68	DMP GNN baseline actual #68 vs paper #68	0.8919	actual #68 vs paper #68 paper 0.8919 prev best: Heterophily-Aware Graph Attention Network (2023) Improvement within reported uncertainty; not highlighted. paper 0.8919 Δ at pub 0.0755
70	GCNII GNN baseline actual #70 vs paper #398 328 places worse	0.8918 ±0.0443 best reported	actual #70 vs paper #398 328 places worse paper 0.6946 ±0.0383 best at pub: Global-Local Graph Neural Networks for Node-Classification (2024) best today: Piecewise Constant Spectral Graph Neural Network (TMLR 2025) paper 0.6946 ±0.0383 Δ at pub 0.1211 Δ today 0.1972
82	GRAFF GNN baseline	0.8838 ±0.0453	This paper
83	ACMII-GCN GNN baseline	0.8838 ±0.0343	This paper
98	G2 GNN baseline	0.8757 ±0.0386	This paper
104	WRGAT GNN baseline actual #104 vs paper #173 69 places worse	0.8698 best reported	actual #104 vs paper #173 69 places worse paper 0.8362 ±0.0550 best at pub: Global-Local Graph Neural Networks for Node-Classification (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8362 ±0.0550 Δ at pub 0.0336
115	ACMP-GCN Hyb baseline	0.8620 ±0.0300	This paper
121	NSD GNN baseline	0.8595 ±0.0551	This paper
137	GraphCON GNN baseline	0.8540 ±0.0420	This paper
181	MagNet GNN baseline	0.8330 ±0.0610	This paper
211	GAT GNN baseline actual #211 vs paper #533 322 places worse	0.8162 ±0.0645 best reported	actual #211 vs paper #533 322 places worse paper 0.5838 ±0.0663 best at pub: A Quasi-Wasserstein Loss for Learning Graph Neural Networks (WWW 2023) best today: Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models (2025) paper 0.5838 ±0.0663 Δ at pub 0.2162 Δ today 0.2324
217	GRAND GNN baseline actual #217 vs paper #308 91 places worse	0.8140 ±0.0350 best reported	actual #217 vs paper #308 91 places worse paper 0.7568 ±0.0725 best at pub: Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond (2023) best today: When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7568 ±0.0725 Δ at pub 0.0452 Δ today 0.0572
257	GCN GNN baseline actual #257 vs paper #576 319 places worse	0.7933 ±0.0447 best reported	actual #257 vs paper #576 319 places worse paper 0.5216 ±0.0516 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Graph Wave Networks (WWW 2025) paper 0.5216 ±0.0516 Δ at pub 0.2624 Δ today 0.2717
276	MixHop GNN baseline	0.7784 ±0.0773	This paper
325	LINKX GNN baseline	0.7460 ±0.0837	This paper
415	Geom-GCN GNN baseline actual #415 vs paper #415	0.6760 best reported	actual #415 vs paper #415 paper 0.6757 ±0.0272 best at pub: Non-Local Graph Neural Networks (2020) Difference within reported uncertainty; not counted as underperformance. paper 0.6757 ±0.0272 Δ at pub 0.0003

Cornell

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	P^2GNN Hyb global	0.9541 ±0.0272	$P^2$GNN: Two Prototype Sets to boost GNN Performance
2	ACM-GCN code ↗ GNN global	0.9480 ±0.0380	Heterophily-informed Message Passing code ↗
3	RF-GCN GNN global	0.9429	Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
12	RDGNN-I Hyb ★ proposed	0.9272 ±0.0588	This paper
14	RDGNN-S GNN ★ proposed	0.9243 ±0.0551	This paper
15	GGCN GNN baseline actual #15 vs paper #79 64 places worse	0.9230 ±0.0367 best reported	actual #15 vs paper #79 64 places worse paper 0.8568 ±0.0663 best at pub: Understanding convolution on graphs via energies (TMLR 2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8568 ±0.0663 Δ today 0.0662
22	GPRGNN GNN baseline actual #22 vs paper #177 155 places worse	0.9157 ±0.0196 best reported	actual #22 vs paper #177 155 places worse paper 0.8027 ±0.0811 best at pub: Simplified PCNet with Robustness (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8027 ±0.0811 Δ at pub 0.1130
24	MLP Trad global	0.9136 ±0.0070	Node-oriented Spectral Filtering for Graph Neural Networks
29	PDE-GCNM GNN baseline	0.8973	This paper
31	DMP GNN baseline actual #31 vs paper #31	0.8919	actual #31 vs paper #31 paper 0.8919 prev best: Heterophily-Aware Graph Attention Network (2023) Improvement within reported uncertainty; not highlighted. paper 0.8919 Δ at pub 0.0219
35	GCNII GNN baseline actual #35 vs paper #233 198 places worse	0.8918 ±0.0396 best reported	actual #35 vs paper #233 198 places worse paper 0.7486 ±0.0379 best at pub: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited (NeurIPS 2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.7486 ±0.0379 Δ at pub 0.0940 Δ today 0.1432
38	FAGCN GNN baseline actual #38 vs paper #185 147 places worse	0.8852 ±0.0133 best reported	actual #38 vs paper #185 147 places worse paper 0.7919 ±0.0587 best at pub: Node-oriented Spectral Filtering for Graph Neural Networks (2022) paper 0.7919 ±0.0587 Δ at pub 0.0933
49	G2 GNN baseline	0.8730 ±0.0484	This paper
52	GREAD GNN baseline actual #52 vs paper #52	0.8703 ±0.0495	actual #52 vs paper #52 paper 0.8703 ±0.0495 prev best: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory (KDD 2024) paper 0.8703 ±0.0495 Δ at pub 0.1325
62	NSD GNN baseline	0.8649 ±0.0471	This paper
63	ACMII-GCN GNN baseline	0.8649 ±0.0673	This paper
68	H2GCN GNN baseline actual #68 vs paper #136 68 places worse	0.8623 ±0.0471 best reported	actual #68 vs paper #136 68 places worse paper 0.8270 ±0.0528 best at pub: Design your own universe: a physics-informed agnostic method for enhancing graph neural networks (2024) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8270 ±0.0528 Δ at pub 0.0240 Δ today 0.0353
83	ACMP-GCN Hyb baseline	0.8540 ±0.0700	This paper
106	MagNet GNN baseline actual #106 vs paper #106	0.8430 ±0.0700	actual #106 vs paper #106 paper 0.8430 ±0.0700 prev best: Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification (2023) Improvement within reported uncertainty; not highlighted. paper 0.8430 ±0.0700 Δ at pub 0.0490
107	GraphCON GNN baseline	0.8430 ±0.0480	This paper
112	GRAFF GNN baseline	0.8405 ±0.0610	This paper
123	LINKX GNN baseline actual #123 vs paper #203 80 places worse	0.8346 ±0.0061 best reported	actual #123 vs paper #203 80 places worse paper 0.7784 ±0.0581 best at pub: Differentiable Cluster Graph Neural Network (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7784 ±0.0581 Δ at pub 0.0562
138	SAGE GNN global	0.8269	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
142	GRAND GNN baseline actual #142 vs paper #151 9 places worse	0.8246 ±0.0709 best reported	actual #142 vs paper #151 9 places worse paper 0.8216 ±0.0709 best at pub: Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation (2023) best today: Graph Navier–Stokes Networks (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8216 ±0.0709 Δ at pub 0.0004 Δ today 0.0030
158	GAT GNN baseline actual #158 vs paper #434 276 places worse	0.8190 ±0.0540 best reported	actual #158 vs paper #434 276 places worse paper 0.5432 ±0.0505 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) paper 0.5432 ±0.0505 Δ at pub 0.2758
160	WRGAT GNN baseline	0.8162 ±0.0390	This paper
170	GCN GNN baseline actual #170 vs paper #459 289 places worse	0.8082 ±0.0360 best reported	actual #170 vs paper #459 289 places worse paper 0.5270 ±0.0530 best at pub: Differentiable Cluster Graph Neural Network (2024) best today: Bayesian Neighborhood Adaptation for Graph Neural Networks (TMLR 2025) paper 0.5270 ±0.0530 Δ at pub 0.2745 Δ today 0.2812
183	MixHop GNN baseline actual #183 vs paper #249 66 places worse	0.7950 ±0.0630 best reported	actual #183 vs paper #249 66 places worse paper 0.7351 ±0.0634 best at pub: Label-Wise Graph Convolutional Network for Heterophilic Graphs (2021) Difference within reported uncertainty; not counted as underperformance. paper 0.7351 ±0.0634 Δ at pub 0.0599
342	Geom-GCN GNN baseline actual #342 vs paper #369 27 places worse	0.6412 best reported	actual #342 vs paper #369 27 places worse paper 0.6081 ±0.0367 best at pub: Steering Graph Neural Networks with Pinning Control (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.6081 ±0.0367 Δ at pub 0.0331

Actor

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	DiGGR Hyb global	0.4535 ±0.0353	Disentangled Generative Graph Representation Learning
2	TRIGON code ↗ Hyb global	0.4402 ±0.0028	Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks code ↗
3	DoG code ↗ ext data GNN global	0.4320 ±0.0120	Diffusion on Graph: Augmentation of Graph Structure for Node Classification code ↗
38	GCNII GNN baseline actual #38 vs paper #290 252 places worse	0.4082 ±0.0179 best reported	actual #38 vs paper #290 252 places worse paper 0.3287 ±0.0130 best at pub: Feature Expansion for Graph Neural Networks (ICML 2023) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.3287 ±0.0130 Δ at pub 0.0574 Δ today 0.0795
42	MLP Trad global	0.4026 ±0.0108	Heterophily-Aware Graph Attention Network
52	GPRGNN GNN baseline actual #52 vs paper #247 195 places worse	0.3992 ±0.0067 best reported	actual #52 vs paper #247 195 places worse paper 0.3463 ±0.0122 best at pub: LON-GNN: Spectral GNNs with Learnable Orthonormal Basis (2023) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.3463 ±0.0122 Δ at pub 0.0529 Δ today 0.0529
56	FAGCN GNN baseline actual #56 vs paper #240 184 places worse	0.3970 best reported	actual #56 vs paper #240 184 places worse paper 0.3487 ±0.0135 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.3487 ±0.0135 Δ at pub 0.0483
62	GGCN GNN baseline actual #62 vs paper #99 37 places worse	0.3929 ±0.0048 best reported	actual #62 vs paper #99 37 places worse paper 0.3781 ±0.0156 best at pub: Feature Transportation Improves Graph Neural Networks (AAAI 2023) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.3781 ±0.0156 Δ today 0.0148
68	GraphSAGE code ↗ GNN global	0.3899 ±0.0085	A Quasi-Wasserstein Loss for Learning Graph Neural Networks code ↗
71	H2GCN GNN baseline actual #71 vs paper #198 127 places worse	0.3885 ±0.0117 best reported	actual #71 vs paper #198 127 places worse paper 0.3570 ±0.0100 best at pub: ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting (2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.3570 ±0.0100 Δ at pub 0.0270 Δ today 0.0315
72	RDGNN-I Hyb ★ proposed	0.3869 ±0.0141	This paper
75	WRGAT GNN baseline actual #75 vs paper #158 83 places worse	0.3860 ±0.0110 best reported	actual #75 vs paper #158 83 places worse paper 0.3653 ±0.0077 best at pub: ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting (2022) paper 0.3653 ±0.0077 Δ at pub 0.0207
78	RDGNN-S GNN ★ proposed	0.3855 ±0.0134	This paper
87	Geom-GCN GNN baseline actual #87 vs paper #305 218 places worse	0.3810 best reported	actual #87 vs paper #305 218 places worse paper 0.3163 ±0.0115 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.3163 ±0.0115 Δ at pub 0.0647
96	GREAD GNN baseline actual #96 vs paper #96	0.3790 ±0.0117	actual #96 vs paper #96 paper 0.3790 ±0.0117 prev best: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory (KDD 2024) Improvement within reported uncertainty; not highlighted. paper 0.3790 ±0.0117 Δ at pub 0.0031
100	NSD GNN baseline actual #100 vs paper #105 5 places worse	0.3781 ±0.0115 best reported	actual #100 vs paper #105 5 places worse paper 0.3779 ±0.0115 best at pub: Graph Parsing Networks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.3779 ±0.0115 Δ at pub 0.0002
120	G2 GNN baseline	0.3730 ±0.0101	This paper
122	DMP GNN baseline actual #122 vs paper #197 75 places worse	0.3726 ±0.0179 best reported	actual #122 vs paper #197 75 places worse paper 0.3572 best at pub: Heterophily-Aware Graph Attention Network (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.3572 Δ at pub 0.0154
129	GRAFF GNN baseline	0.3711 ±0.0108	This paper
131	ACMII-GCN GNN baseline	0.3709 ±0.0132	This paper
135	GCN GNN baseline actual #135 vs paper #411 276 places worse	0.3690 best reported	actual #135 vs paper #411 276 places worse paper 0.2686 ±0.0110 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.2686 ±0.0110 Δ at pub 0.1004
162	MixHop GNN baseline actual #162 vs paper #297 135 places worse	0.3648 ±0.0120 best reported	actual #162 vs paper #297 135 places worse paper 0.3222 ±0.0234 best at pub: Towards Deep Attention in Graph Neural Networks: Problems and Remedies (ICML 2023) paper 0.3222 ±0.0234 Δ at pub 0.0426
180	LINKX GNN baseline	0.3610 ±0.0155	This paper
182	GAT GNN baseline actual #182 vs paper #385 203 places worse	0.3605 ±0.0035 best reported	actual #182 vs paper #385 203 places worse paper 0.2845 ±0.0089 best at pub: Hierarchical Graph Transformer with Adaptive Node Sampling (NeurIPS 2022) paper 0.2845 ±0.0089 Δ at pub 0.0760
203	GRAND GNN baseline	0.3562 ±0.0101	This paper

Squirrel

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	IBG-NN GNN global	0.7763 ±0.0179	Efficient Learning on Large Graphs using a Densifying Regularity Lemma
2	Dir-GNN+CNA code ↗ GNN global	0.7747 ±0.0128	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
3	DHGNN GNN global	0.7684 ±0.0161	Directed Homophily-Aware Graph Neural Network
26	ACMII-GCN GNN baseline	0.6740 ±0.0221	This paper
27	RDGNN-S GNN ★ proposed	0.6596 ±0.0211	This paper
28	RDGNN-I Hyb ★ proposed	0.6562 ±0.0233	This paper
32	G2 GNN baseline	0.6426 ±0.0238	This paper
39	H2GCN GNN baseline actual #39 vs paper #202 163 places worse	0.6190 ±0.0140 best reported	actual #39 vs paper #202 163 places worse paper 0.3648 ±0.0186 best at pub: Optimization-Induced Graph Implicit Nonlinear Diffusion (ICML 2022) best today: Efficient Learning on Large Graphs using a Densifying Regularity Lemma (2025) paper 0.3648 ±0.0186 Δ at pub 0.0427 Δ today 0.2542
40	LINKX GNN baseline	0.6181 ±0.0180	This paper
46	GCN GNN baseline actual #46 vs paper #267 221 places worse	0.6067 best reported	actual #46 vs paper #267 221 places worse paper 0.2396 ±0.0201 best at pub: Understanding Heterophily for Graph Neural Networks (ICML 2024) paper 0.2396 ±0.0201 Δ at pub 0.3671
51	GREAD GNN baseline	0.5922 ±0.0144	This paper
53	GRAFF GNN baseline	0.5901 ±0.0131	This paper
65	NSD GNN baseline	0.5634 ±0.0132	This paper
67	GAT GNN baseline actual #67 vs paper #241 174 places worse	0.5630 ±0.0220 best reported	actual #67 vs paper #241 174 places worse paper 0.3003 ±0.0155 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) paper 0.3003 ±0.0155 Δ at pub 0.2627
69	GGCN GNN baseline actual #69 vs paper #71 2 places worse	0.5567 ±0.0187 best reported	actual #69 vs paper #71 2 places worse paper 0.5517 ±0.0158 best at pub: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.5517 ±0.0158 Δ today 0.0050
76	GPRGNN GNN baseline actual #76 vs paper #235 159 places worse	0.5435 ±0.0087 best reported	actual #76 vs paper #235 159 places worse paper 0.3161 ±0.0124 best at pub: LON-GNN: Spectral GNNs with Learnable Orthonormal Basis (2023) best today: Directed Homophily-Aware Graph Neural Network (2025) paper 0.3161 ±0.0124 Δ at pub 0.1854 Δ today 0.2274
96	WRGAT GNN baseline	0.4885 ±0.0078	This paper
101	DMP GNN baseline	0.4726	This paper
120	SAGE code ↗ GNN global	0.4460 ±0.0130	Scale-aware Message Passing For Graph Node Classification code ↗
127	MixHop GNN baseline	0.4380 ±0.0148	This paper
139	FAGCN GNN baseline	0.4259 ±0.0069	This paper
164	GRAND GNN baseline	0.4005 ±0.0150	This paper
172	MLP code ↗ Trad global	0.3930 ±0.0079	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
176	GCNII GNN baseline actual #176 vs paper #178 2 places worse	0.3881 ±0.0197 best reported	actual #176 vs paper #178 2 places worse paper 0.3847 ±0.0158 best at pub: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.3847 ±0.0158 Δ today 0.0034
179	Geom-GCN GNN baseline	0.3832 ±0.0092	This paper

LINKX Benchmarks

arxiv-year

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	LargeScaleNet code ↗ Hyb global	0.6582 ±0.0036	Scale-aware Message Passing For Graph Node Classification code ↗
2	S² DirGCN global	0.6495 ±0.0033	Spatio-Spectral Graph Neural Networks
3	FaberNet code ↗ GNN global	0.6462 ±0.0101	Scale-aware Message Passing For Graph Node Classification code ↗
11	RDGNN-I Hyb ★ proposed	0.5846 ±0.0059	This paper
13	LINKX GNN baseline	0.5600 ±0.0134	This paper
15	RDGNN-S GNN ★ proposed	0.5516 ±0.0046	This paper
17	LINK Hyb baseline	0.5397 ±0.0018	This paper
19	MixHop GNN baseline	0.5181 ±0.0017	This paper
22	GAT GNN baseline actual #22 vs paper #30 8 places worse	0.4937 ±0.0020 best reported	actual #22 vs paper #30 8 places worse paper 0.4605 ±0.0051 best at pub: Uplifting Message Passing Neural Network with Graph Original Information (2022) paper 0.4605 ±0.0051 Δ at pub 0.0332
23	H2GCN GNN baseline actual #23 vs paper #23	0.4910 ±0.0010 best reported	actual #23 vs paper #23 paper 0.4909 ±0.0010 best at pub: Label-Wise Graph Convolutional Network for Heterophilic Graphs (2021) Difference within reported uncertainty; not counted as underperformance. paper 0.4909 ±0.0010 Δ at pub 0.0001
26	GCNII GNN baseline	0.4721 ±0.0028	This paper
30	L Prop (2 hop) GNN baseline	0.4607 ±0.0015	This paper
31	GCN GNN baseline	0.4602 ±0.0026	This paper
32	GPR-GNN GNN baseline actual #32 vs paper #34 2 places worse	0.4597 ±0.0026 best reported	actual #32 vs paper #34 2 places worse paper 0.4507 ±0.0021 best at pub: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited (NeurIPS 2022) paper 0.4507 ±0.0021 Δ at pub 0.0090
40	C&S (2 hop) GNN baseline	0.4217 ±0.0027	This paper
53	APPNP GNN baseline	0.3815 ±0.0026	This paper
56	MLP Trad baseline	0.3670 ±0.0021	This paper
59	SGC (2 hop) GNN baseline	0.3227 ±0.0006	This paper

SOTA performance (not significantly different from the best) Proposed method (this paper) Baseline / comparison (this paper) Global context (other papers) Best at pub — reported result worse than the best known when published (best reported in green) Best at pub — reported value improved over the best known when published Best today — OK at publication; today's leaderboard best is elsewhere