Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

Qiyu Kang, Kai Zhao, Qinxu Ding, Feng Ji, Xuhao Li, Wenfei Liang, Yang Song, Wee Peng Tay

Abstract

We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on integer-order differential equations, FROND employs the Caputo fractional derivative to leverage the non-local properties of fractional calculus. This approach enables the capture of long-term dependencies in feature updates, moving beyond the Markovian update mechanisms in conventional integer-order models and offering enhanced capabilities in graph representation learning. We offer an interpretation of the node feature updating process in FROND from a non-Markovian random walk perspective when the feature updating is particularly governed by a diffusion process. We demonstrate analytically that oversmoothing can be mitigated in this setting. Experimentally, we validate the FROND framework by comparing the fractional adaptations of various established integer-order continuous GNNs, demonstrating their consistently improved performance and underscoring the framework's potential as an effective extension to enhance traditional continuous GNNs. The code is available at.

Benchmark Results

Tested on 10 datasets SOTA at publication on 1 13 baseline values reported too low

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

Classic

Amazon-Photo

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	GraphTARIF code ↗ Hyb global	0.9703 ±0.0019	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
2	GAT GNN baseline actual #2 vs paper #503 501 places worse	0.9669 ±0.0014 best reported	actual #2 vs paper #503 501 places worse paper 0.8570 ±0.2030 best at pub: SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning (2023) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8570 ±0.2030 Δ at pub 0.0928 Δ today 0.1099
3	GAT+T code ↗ Hyb global	0.9660 ±0.0007	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
7	SAGE code ↗ GNN global	0.9643 ±0.0027	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
8	GCN GNN baseline actual #8 vs paper #395 387 places worse	0.9632 ±0.0008 best reported	actual #8 vs paper #395 387 places worse paper 0.9120 ±0.0120 best at pub: SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning (2023) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) paper 0.9120 ±0.0120 Δ at pub 0.0356 Δ today 0.0512
182	RL-GRAND-l GNN baseline	0.9330 ±0.0070	This paper
207	F-GRAND-nl GNN ★ proposed	0.9310 ±0.0090	This paper
239	F-GRAND-l GNN ★ proposed	0.9280 ±0.0060	This paper
298	GRAND-nl GNN ★ proposed	0.9240 ±0.0080	This paper
310	GRAND-l GNN ★ proposed	0.9230 ±0.0090	This paper
390	MLP code ↗ Trad global	0.9128 ±0.0063	Clarify Confused Nodes via Separated Learning code ↗
461	GIL GNN baseline	0.8960 ±0.0130	This paper
489	HGCN GNN baseline	0.8820 ±0.0140	This paper

Amazon-Computers

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	GraphTARIF code ↗ Hyb global	0.9461 ±0.0017	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
2	GCN GNN baseline actual #2 vs paper #389 387 places worse	0.9412 ±0.0008 best reported	actual #2 vs paper #389 387 places worse paper 0.8260 ±0.0240 best at pub: Clarify Confused Nodes via Separated Learning (2023) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) paper 0.8260 ±0.0240 Δ at pub 0.0712 Δ today 0.1152
3	GAT GNN baseline actual #3 vs paper #442 439 places worse	0.9398 ±0.0022 best reported	actual #3 vs paper #442 439 places worse paper 0.7800 ±0.1900 best at pub: SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning (2023) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.7800 ±0.1900 Δ at pub 0.1278 Δ today 0.1598
8	SAGE code ↗ GNN global	0.9351 ±0.0006	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
320	MLP code ↗ Trad global	0.8463	GraphFM: A generalist graph transformer that learns transferable representations across diverse … code ↗
332	F-GRAND-l GNN ★ proposed	0.8440 ±0.0150	This paper
348	F-GRAND-nl GNN ★ proposed	0.8410 ±0.0090	This paper
360	GRAND-l GNN ★ proposed	0.8370 ±0.0120	This paper
394	GRAND-nl GNN ★ proposed	0.8240 ±0.0210	This paper
426	HGCN GNN baseline	0.8060 ±0.0180	This paper

OGB

ogbn-products

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	Jacobi GNN global	0.8968	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
2	GPR GNN global	0.8953	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
3	LEMP4HG ext data Hyb global	0.8939	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
4	SAGE GNN global	0.8933	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
83	GraphSAGE GNN baseline actual #83 vs paper #215 132 places worse	0.8287 best reported	actual #83 vs paper #215 132 places worse paper 0.7829 ±0.0016 best at pub: A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking (NeurIPS 2022) best today: Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning (ICML 2026) paper 0.7829 ±0.0016 Δ at pub 0.0232 Δ today 0.0458
229	F-GRAND-l GNN ★ proposed	0.7725 ±0.0062	This paper
251	Full-batch GCN GNN baseline	0.7564 ±0.0021	This paper
257	GRAND-l GNN ★ proposed	0.7556 ±0.0067	This paper
313	Node2Vec Walk baseline	0.7249 ±0.0010	This paper
351	MLP Trad baseline actual #351 vs paper #370 19 places worse	0.6605 ±0.0020 best reported	actual #351 vs paper #370 19 places worse paper 0.6106 ±0.0008 best at pub: SCR: Training Graph Neural Networks with Consistency Regularization (2021) best today: Latent Graph Inference using Product Manifolds (ICLR 2022) paper 0.6106 ±0.0008 Δ at pub 0.2312 Δ today 0.0499

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 ↗
5	ACM-GCN GNN baseline actual #5 vs paper #91 86 places worse	0.9557 ±0.0360 best reported	actual #5 vs paper #91 86 places worse paper 0.8784 ±0.0440 best at pub: From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm (2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.8784 ±0.0440 Δ today 0.0773
27	F-GREAD-BS GNN baseline	0.9297 ±0.0439	This paper
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: Understanding convolution on graphs via energies (TMLR 2022) best today: Graph Wave Networks (WWW 2025) paper 0.8486 ±0.0455 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: How Curvature Enhance the Adaptation Power of Framelet GCNs (2023) 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 0.0104 Δ today 0.0703
53	GraphSAGE code ↗ GNN global	0.9000 ±0.0365	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
70	GCNII GNN baseline actual #70 vs paper #280 210 places worse	0.8918 ±0.0443 best reported	actual #70 vs paper #280 210 places worse paper 0.7757 ±0.0383 best at pub: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited (NeurIPS 2022) best today: Piecewise Constant Spectral Graph Neural Network (TMLR 2025) paper 0.7757 ±0.0383 Δ at pub 0.0289 Δ today 0.1161
75	GREAD-BS Hyb baseline actual #75 vs paper #75	0.8892 ±0.0372	actual #75 vs paper #75 paper 0.8892 ±0.0372 prev best: Graph Neural Aggregation-diffusion with Metastability (2024) Improvement within reported uncertainty; not highlighted. paper 0.8892 ±0.0372 Δ at pub 0.0002
82	GRAFF GNN baseline	0.8838 ±0.0453	This paper
141	GloGNN GNN baseline actual #141 vs paper #164 23 places worse	0.8524 ±0.0490 best reported	actual #141 vs paper #164 23 places worse paper 0.8432 ±0.0415 best at pub: Finding Global Homophily in Graph Neural Networks When Meeting Heterophily (ICML 2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8432 ±0.0415 Δ today 0.0092
145	Sheaf GNN baseline	0.8505 ±0.0551	This paper
182	BLEND GNN baseline	0.8324 ±0.0465	This paper
217	GRAND GNN ★ proposed 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
325	LINKX GNN baseline	0.7460 ±0.0837	This paper
376	CGNN GNN baseline actual #376 vs paper #378 2 places worse	0.7140 ±0.0410 best reported	actual #376 vs paper #378 2 places worse paper 0.7135 ±0.0405 best at pub: Graph Neural Aggregation-diffusion with Metastability (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7135 ±0.0405 Δ at pub 0.0005
415	Geom-GCN GNN baseline actual #415 vs paper #425 10 places worse	0.6760 best reported	actual #415 vs paper #425 10 places worse paper 0.6676 ±0.0272 best at pub: Non-Local Graph Neural Networks (2020) Difference within reported uncertainty; not counted as underperformance. paper 0.6676 ±0.0272 Δ at pub 0.0084

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 ↗
16	ACM-GCN GNN baseline actual #16 vs paper #173 157 places worse	0.4198 ±0.0089 best reported	actual #16 vs paper #173 157 places worse paper 0.3628 ±0.0109 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 0.3628 ±0.0109 Δ at pub 0.0032 Δ today 0.0570
38	GCNII GNN baseline actual #38 vs paper #114 76 places worse	0.4082 ±0.0179 best reported	actual #38 vs paper #114 76 places worse paper 0.3744 ±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 0.3744 ±0.0130 Δ at pub 0.0117 Δ today 0.0338
42	MLP Trad global	0.4026 ±0.0108	Heterophily-Aware Graph Attention Network
58	GloGNN GNN baseline actual #58 vs paper #116 58 places worse	0.3959 ±0.0029 best reported	actual #58 vs paper #116 58 places worse paper 0.3735 ±0.0130 best at pub: SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning (2023) paper 0.3735 ±0.0130 Δ at pub 0.0224
62	GGCN GNN baseline actual #62 vs paper #113 51 places worse	0.3929 ±0.0048 best reported	actual #62 vs paper #113 51 places worse paper 0.3754 ±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 0.3754 ±0.0156 Δ at pub 0.0027 Δ today 0.0175
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
82	F-GREAD-BS GNN baseline	0.3828 ±0.0074	This paper
87	Geom-GCN GNN baseline actual #87 vs paper #308 221 places worse	0.3810 best reported	actual #87 vs paper #308 221 places worse paper 0.3159 ±0.0115 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.3159 ±0.0115 Δ at pub 0.0651
94	GREAD-BS Hyb baseline	0.3790 ±0.0117	This paper
102	Sheaf GNN baseline	0.3781 ±0.0115	This paper
129	GRAFF GNN baseline actual #129 vs paper #181 52 places worse	0.3711 ±0.0108 best reported	actual #129 vs paper #181 52 places worse paper 0.3609 ±0.0081 best at pub: Understanding convolution on graphs via energies (TMLR 2022) best today: Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.3609 ±0.0081 Δ at pub 0.0102 Δ today 0.0102
180	LINKX GNN baseline	0.3610 ±0.0155	This paper
189	CGNN GNN baseline	0.3595 ±0.0086	This paper
201	BLEND GNN baseline	0.3563 ±0.0101	This paper
203	GRAND GNN ★ proposed	0.3562 ±0.0101	This paper

Chameleon

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	Hetero-S (GAT 8-layer) code ↗ Hyb global	0.8693	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs code ↗
2	Dir-GNN+CNA code ↗ GNN global	0.8586 ±0.0180	Graph Neural Networks Need Cluster-Normalize-Activate Modules code ↗
3	GAT code ↗ GNN global	0.8560	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs code ↗
28	ACM-GCN GNN baseline actual #28 vs paper #76 48 places worse	0.7476 ±0.0220 best reported	actual #28 vs paper #76 48 places worse paper 0.6693 ±0.0185 best at pub: From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm (2022) best today: Directed Homophily-Aware Graph Neural Network (2025) paper 0.6693 ±0.0185 Δ today 0.0783
41	F-GREAD-BS GNN baseline	0.7145 ±0.0198	This paper
42	GREAD-BS Hyb baseline actual #42 vs paper #44 2 places worse	0.7142 ±0.0178 best reported	actual #42 vs paper #44 2 places worse paper 0.7138 ±0.0131 best at pub: Graph Neural Aggregation-diffusion with Metastability (2024) best today: Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.7138 ±0.0131 Δ at pub 0.0002 Δ today 0.0004
45	GloGNN GNN baseline actual #45 vs paper #56 11 places worse	0.7133 ±0.0242 best reported	actual #45 vs paper #56 11 places worse paper 0.6978 ±0.0242 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 0.6978 ±0.0242 Δ at pub 0.0143 Δ today 0.0155
48	GGCN GNN baseline	0.7114 ±0.0184	This paper
49	GRAFF GNN baseline	0.7108 ±0.0175	This paper
52	GCN GNN global	0.7033	Understanding Heterophily for Graph Neural Networks
64	LINKX GNN baseline	0.6842 ±0.0138	This paper
69	Sheaf GNN baseline	0.6804 ±0.0158	This paper
103	GCNII GNN baseline	0.6386 ±0.0304	This paper
124	Geom-GCN GNN baseline actual #124 vs paper #137 13 places worse	0.6090 best reported	actual #124 vs paper #137 13 places worse paper 0.6000 ±0.0281 best at pub: Non-Local Graph Neural Networks (2020) best today: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating (AAAI 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.6000 ±0.0281 Δ at pub 0.0090 Δ today 0.0090
133	H2GCN GNN baseline actual #133 vs paper #136 3 places worse	0.6030 ±0.0231 best reported	actual #133 vs paper #136 3 places worse paper 0.6011 ±0.0215 best at pub: Optimization-Induced Graph Implicit Nonlinear Diffusion (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.6011 ±0.0215 Δ at pub 0.0019
137	BLEND GNN baseline	0.6011 ±0.0209	This paper
143	CGNN GNN baseline actual #143 vs paper #215 72 places worse	0.5910 ±0.0078 best reported	actual #143 vs paper #215 72 places worse paper 0.4689 ±0.0166 best at pub: Graph Neural Aggregation-diffusion with Metastability (2024) best today: Gauge-Equivariant Graph Networks via Self-Interference Cancellation (2025) paper 0.4689 ±0.0166 Δ at pub 0.0001 Δ today 0.1221
151	GRAND GNN baseline actual #151 vs paper #167 16 places worse	0.5467 ±0.0254	actual #151 vs paper #167 16 places worse paper 0.5467 ±0.0254 prev best: TIDE: Time Derivative Diffusion for Deep Learning on Graphs (ICML 2022) paper 0.5467 ±0.0254 Δ at pub 0.0434
169	MLP Trad global	0.5429	Understanding Heterophily for Graph Neural Networks

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
19	GloGNN GNN baseline actual #19 vs paper #57 38 places worse	0.7121 ±0.0184 best reported	actual #19 vs paper #57 38 places worse paper 0.5754 ±0.0139 best at pub: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) best today: Directed Homophily-Aware Graph Neural Network (2025) paper 0.5754 ±0.0139 Δ at pub 0.0034 Δ today 0.1367
25	ACM-GCN GNN baseline actual #25 vs paper #75 50 places worse	0.6740 ±0.0221 best reported	actual #25 vs paper #75 50 places worse paper 0.5440 ±0.0188 best at pub: From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm (2022) best today: Directed Homophily-Aware Graph Neural Network (2025) paper 0.5440 ±0.0188 Δ today 0.1300
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
45	F-GREAD-BS GNN baseline	0.6086 ±0.0105	This paper
46	GCN GNN global	0.6067	Understanding Heterophily for Graph Neural Networks
52	GREAD-BS Hyb baseline actual #52 vs paper #52	0.5922 ±0.0144	actual #52 vs paper #52 paper 0.5922 ±0.0144 prev best: Graph Neural Aggregation-diffusion with Metastability (2024) Improvement within reported uncertainty; not highlighted. paper 0.5922 ±0.0144 Δ at pub 0.0002
53	GRAFF GNN baseline actual #53 vs paper #75 22 places worse	0.5901 ±0.0131 best reported	actual #53 vs paper #75 22 places worse paper 0.5452 ±0.0137 best at pub: Feature Transportation Improves Graph Neural Networks (AAAI 2023) best today: Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. (2024) paper 0.5452 ±0.0137 Δ at pub 0.0449 Δ today 0.0449
66	Sheaf GNN baseline	0.5634 ±0.0132	This paper
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
132	BLEND GNN baseline	0.4306 ±0.0139	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 actual #179 vs paper #181 2 places worse	0.3832 ±0.0092 best reported	actual #179 vs paper #181 2 places worse paper 0.3815 ±0.0092 best at pub: Feature Transportation Improves Graph Neural Networks (AAAI 2023) best today: Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.3815 ±0.0092 Δ at pub 0.0017 Δ today 0.0017
228	CGNN GNN baseline actual #228 vs paper #242 14 places worse	0.2924 ±0.0109	actual #228 vs paper #242 14 places worse paper 0.2924 ±0.0109 prev best: Graph Neural Aggregation-diffusion with Metastability (2024) best today: Gauge-Equivariant Graph Networks via Self-Interference Cancellation (2025) Improvement within reported uncertainty; not highlighted. paper 0.2924 ±0.0109 Δ at pub 0.0004 Δ today 0.0516

Wisconsin

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	DMD++ Hyb global	0.9190 ±0.0260	When Graph Neural Networks Meet Dynamic Mode Decomposition
2	F-GREAD-BS GNN baseline	0.9059 ±0.0380	This paper
3	APPNP GNN global	0.9010 ±0.0350	When Graph Neural Networks Meet Dynamic Mode Decomposition
7	GREAD-BS Hyb baseline	0.8941 ±0.0330	This paper
8	Sheaf GNN baseline	0.8941 ±0.0474	This paper
13	GRAND GNN ★ proposed actual #13 vs paper #80 67 places worse	0.7941 ±0.0364	actual #13 vs paper #80 67 places worse paper 0.7941 ±0.0364 prev best: TIDE: Time Derivative Diffusion for Deep Learning on Graphs (ICML 2022) best today: When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2024) paper 0.7941 ±0.0364 Δ at pub 0.1455 Δ today 0.0919
15	ACM-GCN GNN baseline	0.8843 ±0.0322	This paper
22	H2GCN GNN baseline actual #22 vs paper #23 1 place worse	0.8765 ±0.0498	actual #22 vs paper #23 1 place worse paper 0.8765 ±0.0498 prev best: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating (AAAI 2022) Improvement within reported uncertainty; not highlighted. paper 0.8765 ±0.0498 Δ at pub 0.0098
24	GRAFF GNN baseline	0.8745 ±0.0294	This paper
27	GloGNN GNN baseline	0.8706 ±0.0353	This paper
32	GGCN GNN baseline	0.8686 ±0.0329	This paper
37	MLP code ↗ Trad global	0.8629 ±0.0450	Is Homophily a Necessity for Graph Neural Networks? code ↗
57	BLEND GNN baseline	0.8412 ±0.0356	This paper
63	GCN code ↗ GNN global	0.8310 ±0.0320	Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering code ↗
75	GCNII GNN baseline	0.8039 ±0.0340	This paper
97	LINKX GNN baseline	0.7549 ±0.0572	This paper
110	CGNN GNN baseline	0.7431 ±0.0726	This paper
139	Geom-GCN GNN baseline actual #139 vs paper #149 10 places worse	0.6451 ±0.0366	actual #139 vs paper #149 10 places worse paper 0.6451 ±0.0366 prev best: Non-Local Graph Neural Networks (2020) Improvement within reported uncertainty; not highlighted. paper 0.6451 ±0.0366 Δ at pub 0.0041

Heterophily Benchmark

Roman-empire

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	Dir-Poly code ↗ GNN global	0.9451 ±0.0022	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
2	D-CDE code ↗ GNN global	0.9387 ±0.0041	Distributed-Order Fractional Graph Operating Network code ↗
3	LargeScaleNet code ↗ Hyb global	0.9358 ±0.0024	Scale-aware Message Passing For Graph Node Classification code ↗
6	F-CDE GNN baseline	0.9306 ±0.0055	This paper
18	CDE GNN baseline	0.9164 ±0.0028	This paper
26	GraphSAGE code ↗ GNN global	0.9106 ±0.0027	Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding code ↗
105	Diag-NSD Hyb baseline	0.7750 ±0.0067	This paper
107	GBK-GNN GNN baseline actual #107 vs paper #107	0.7587 ±0.0043	actual #107 vs paper #107 paper 0.7587 ±0.0043 prev best: Evolving Computation Graphs (ICML 2023) paper 0.7587 ±0.0043 Δ at pub 0.0130
108	FAGCN GNN baseline actual #108 vs paper #122 14 places worse	0.7053 ±0.0099	actual #108 vs paper #122 14 places worse paper 0.7053 ±0.0099 prev best: Evolving Computation Graphs (ICML 2023) best today: NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification (2024) paper 0.7053 ±0.0099 Δ at pub 0.0531 Δ today 0.0518
114	GPR-GNN GNN baseline actual #114 vs paper #114	0.7337 ±0.0068	actual #114 vs paper #114 paper 0.7337 ±0.0068 prev best: Evolving Computation Graphs (ICML 2023) paper 0.7337 ±0.0068 Δ at pub 0.0852
115	ACM-GCN GNN baseline actual #115 vs paper #128 13 places worse	0.7189 ±0.0061 best reported	actual #115 vs paper #128 13 places worse paper 0.6835 ±0.0195 best at pub: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) best today: ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs (2025) paper 0.6835 ±0.0195 Δ at pub 0.0307 Δ today 0.0354
116	GRAND GNN ★ proposed	0.7160 ±0.0058	This paper
119	ACMP GNN baseline	0.7127 ±0.0059	This paper
126	GraphBel GNN baseline	0.6947 ±0.0037	This paper
129	H2GCN GNN baseline actual #129 vs paper #129	0.6809 ±0.0029	actual #129 vs paper #129 paper 0.6809 ±0.0029 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) paper 0.6809 ±0.0029 Δ at pub 0.0798
135	MLP code ↗ Trad global	0.6665 ±0.0047	HyperAggregation: Aggregating over Graph Edges with Hypernetworks code ↗
141	ResNet Trad baseline actual #141 vs paper #141	0.6588 ±0.0038 best reported	actual #141 vs paper #141 paper 0.6571 ±0.0044 best at pub: Evolving Computation Graphs (ICML 2023) best today: Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.6571 ±0.0044 Δ at pub 0.0017 Δ today 0.0017
152	CPGNN GNN baseline actual #152 vs paper #154 2 places worse	0.6396 ±0.0062 best reported	actual #152 vs paper #154 2 places worse paper 0.6378 ±0.0050 best at pub: Evolving Computation Graphs (ICML 2023) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.6378 ±0.0050 Δ at pub 0.0018 Δ today 0.0018
154	GloGNN GNN baseline actual #154 vs paper #154	0.6385 ±0.0049	actual #154 vs paper #154 paper 0.6385 ±0.0049 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) paper 0.6385 ±0.0049 Δ at pub 0.0422

Amazon-ratings

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	UniGAP global	0.6375 ±0.0110	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node …
2	H2GCN + HalfHop GNN global	0.5961 ±0.0100	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node …
3	GraphSAGE + HalfHop GNN global	0.5897 ±0.0150	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node …
7	H2GCN GNN baseline actual #7 vs paper #182 175 places worse	0.4136 ±0.0047	actual #7 vs paper #182 175 places worse paper 0.4136 ±0.0047 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) best today: UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks (2024) paper 0.4136 ±0.0047 Δ at pub 0.0489 Δ today 0.1545
12	SAGE code ↗ GNN global	0.5569 ±0.0023	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
47	ACM-GCN GNN baseline actual #47 vs paper #191 144 places worse	0.5294 ±0.0023 best reported	actual #47 vs paper #191 144 places worse paper 0.3851 ±0.0338 best at pub: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) paper 0.3851 ±0.0338 Δ at pub 0.1443
84	MLP Trad global	0.5058	Understanding Heterophily for Graph Neural Networks
103	GPR-GNN GNN baseline actual #103 vs paper #159 56 places worse	0.4937 ±0.0071 best reported	actual #103 vs paper #159 56 places worse paper 0.4390 ±0.0048 best at pub: Evolving Computation Graphs (ICML 2023) best today: Piecewise Constant Spectral Graph Neural Network (TMLR 2025) paper 0.4390 ±0.0048 Δ at pub 0.0098 Δ today 0.0547
106	F-CDE GNN baseline	0.4901 ±0.0056	This paper
127	CDE GNN baseline	0.4763 ±0.0043	This paper
137	FAGCN GNN baseline actual #137 vs paper #137	0.4632 ±0.0250	actual #137 vs paper #137 paper 0.4632 ±0.0250 prev best: Evolving Computation Graphs (ICML 2023) Improvement within reported uncertainty; not highlighted. paper 0.4632 ±0.0250 Δ at pub 0.0220
140	GBK-GNN GNN baseline actual #140 vs paper #162 22 places worse	0.4598 ±0.0071 best reported	actual #140 vs paper #162 22 places worse paper 0.4347 ±0.0051 best at pub: Evolving Computation Graphs (ICML 2023) best today: Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow (2026) paper 0.4347 ±0.0051 Δ at pub 0.0251 Δ today 0.0251
141	ResNet Trad baseline actual #141 vs paper #142 1 place worse	0.4590 ±0.0052 best reported	actual #141 vs paper #142 1 place worse paper 0.4570 ±0.0069 best at pub: Evolving Computation Graphs (ICML 2023) best today: Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.4570 ±0.0069 Δ at pub 0.0020 Δ today 0.0020
148	GRAND GNN ★ proposed	0.4505 ±0.0065	This paper
151	ACMP GNN baseline	0.4476 ±0.0052	This paper
154	CPGNN GNN baseline actual #154 vs paper #154	0.4436 ±0.0035	actual #154 vs paper #154 paper 0.4436 ±0.0035 prev best: Evolving Computation Graphs (ICML 2023) paper 0.4436 ±0.0035 Δ at pub 0.0457
162	GraphBel GNN baseline	0.4363 ±0.0042	This paper
194	Diag-NSD Hyb baseline	0.3796 ±0.0020	This paper
196	GloGNN GNN baseline actual #196 vs paper #196	0.3728 ±0.0066	actual #196 vs paper #196 paper 0.3728 ±0.0066 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) Improvement within reported uncertainty; not highlighted. paper 0.3728 ±0.0066 Δ at pub 0.0039

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 Improved at pub — later paper surpassed this result Best today — OK at publication; today's leaderboard best is elsewhere