Gradient Gating for Deep Multi-Rate Learning on Graphs

T. Konstantin Rusch, B. Chamberlain, Michael W. Mahoney, Michael M. Bronstein, Siddhartha Mishra

Abstract

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph. Local gradients are harnessed to further modulate message passing updates. Our framework flexibly allows one to use any basic GNN layer as a wrapper around which the multi-rate gradient gating mechanism is built. We rigorously prove that G$^2$ alleviates the oversmoothing problem and allows the design of deep GNNs. Empirical results are presented to demonstrate that the proposed framework achieves state-of-the-art performance on a variety of graph learning tasks, including on large-scale heterophilic graphs.

Benchmark Results

Tested on 7 datasets 21 baseline values reported too low

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

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 ↗
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: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.7838 ±0.0436 Δ at pub 0.0622 Δ today 0.1457
34	MLP Trad baseline actual #34 vs paper #230 196 places worse	0.9230 ±0.0070 best reported	actual #34 vs paper #230 196 places worse paper 0.8081 ±0.0475 best at pub: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited (NeurIPS 2022) best today: Design your own universe: a physics-informed agnostic method for enhancing graph neural networks (2024) paper 0.8081 ±0.0475 Δ at pub 0.0600 Δ today 0.1149
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: Graph-Coupled Oscillator Networks (ICML 2022) 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 0.0004 Δ today 0.0703
53	GraphSAGE GNN baseline actual #53 vs paper #193 140 places worse	0.9000 ±0.0365 best reported	actual #53 vs paper #193 140 places worse paper 0.8243 ±0.0614 best at pub: Graph Neural Networks Inspired by Classical Iterative Algorithms (ICML 2021) best today: Graph Neural Networks Need Cluster-Normalize-Activate Modules (NeurIPS 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8243 ±0.0614 Δ today 0.0757
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 ±0.0689 best at pub: A Piece-wise Polynomial Filtering Approach for Graph Neural Networks (2021) best today: Node-oriented Spectral Filtering for Graph Neural Networks (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.8243 ±0.0689 Δ today 0.0718
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
99	G^2-GraphSAGE Hyb baseline	0.8757 ±0.0386	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
151	G^2-GCN Hyb baseline	0.8486 ±0.0324	This paper
161	G^2-GAT Hyb baseline	0.8459 ±0.0555	This paper
187	F^2GAT GNN baseline	0.8270 ±0.0595	This paper
189	SAGE GNN global	0.8269	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
211	GAT GNN baseline actual #211 vs paper #576 365 places worse	0.8162 ±0.0645 best reported	actual #211 vs paper #576 365 places worse paper 0.5216 ±0.0663 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models (2025) paper 0.5216 ±0.0663 Δ at pub 0.2764 Δ today 0.2946
242	ResGatedGCN GNN baseline	0.8000 ±0.0557	This paper
257	GCN GNN baseline actual #257 vs paper #568 311 places worse	0.7933 ±0.0447 best reported	actual #257 vs paper #568 311 places worse paper 0.5514 ±0.0516 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Graph Wave Networks (WWW 2025) paper 0.5514 ±0.0516 Δ at pub 0.2326 Δ today 0.2419
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 #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
499	PairNorm GNN baseline actual #499 vs paper #499	0.6030 ±0.0430 best reported	actual #499 vs paper #499 paper 0.6027 ±0.0434 best at pub: Graph-Coupled Oscillator Networks (ICML 2022) best today: Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.6027 ±0.0434 Δ at pub 0.0003 Δ today 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
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: Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks (2022) best today: Simplified PCNet with Robustness (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8027 ±0.0811 Δ at pub 0.0351 Δ today 0.1130
24	MLP Trad baseline actual #24 vs paper #158 134 places worse	0.9136 ±0.0070 best reported	actual #24 vs paper #158 134 places worse paper 0.8189 ±0.0640 best at pub: Is Homophily a Necessity for Graph Neural Networks? (ICLR 2021) best today: Node-oriented Spectral Filtering for Graph Neural Networks (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.8189 ±0.0640 Δ at pub 0.0297 Δ today 0.0947
35	GCNII GNN baseline actual #35 vs paper #203 168 places worse	0.8918 ±0.0396 best reported	actual #35 vs paper #203 168 places worse paper 0.7786 ±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 0.7786 ±0.0379 Δ at pub 0.0640 Δ today 0.1132
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 ±0.0979 best at pub: Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks (2022) best today: Node-oriented Spectral Filtering for Graph Neural Networks (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7919 ±0.0979 Δ at pub 0.0189 Δ today 0.0933
46	G^2-GAT Hyb baseline	0.8730 ±0.0484	This paper
61	G^2-GCN Hyb baseline	0.8649 ±0.0527	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: Graph-Coupled Oscillator Networks (ICML 2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8270 ±0.0528 Δ today 0.0353
70	G^2-GraphSAGE Hyb baseline	0.8622 ±0.0490	This paper
74	GloGNN GNN baseline actual #74 vs paper #119 45 places worse	0.8595 ±0.0510 best reported	actual #74 vs paper #119 45 places worse paper 0.8351 ±0.0426 best at pub: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) best today: Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.8351 ±0.0426 Δ at pub 0.0244 Δ today 0.0244
120	F^2GAT GNN baseline	0.8351 ±0.0670	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: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) best today: Differentiable Cluster Graph Neural Network (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7784 ±0.0581 Δ today 0.0562
138	SAGE GNN global	0.8269	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
157	GraphSAGE GNN baseline actual #157 vs paper #222 65 places worse	0.8196 ±0.0739 best reported	actual #157 vs paper #222 65 places worse paper 0.7595 ±0.0501 best at pub: Graph-Coupled Oscillator Networks (ICML 2022) best today: Heterophily-Aware Graph Attention Network (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.7595 ±0.0501 Δ at pub 0.0005 Δ today 0.0601
158	GAT GNN baseline actual #158 vs paper #358 200 places worse	0.8190 ±0.0540 best reported	actual #158 vs paper #358 200 places worse paper 0.6189 ±0.0505 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) paper 0.6189 ±0.0505 Δ at pub 0.2001
170	GCN GNN baseline actual #170 vs paper #372 202 places worse	0.8082 ±0.0360 best reported	actual #170 vs paper #372 202 places worse paper 0.6054 ±0.0530 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Bayesian Neighborhood Adaptation for Graph Neural Networks (TMLR 2025) paper 0.6054 ±0.0530 Δ at pub 0.1866 Δ today 0.2028
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
251	ResGatedGCN GNN baseline	0.7351 ±0.0495	This paper
342	Geom-GCN GNN baseline actual #342 vs paper #372 30 places worse	0.6412 best reported	actual #342 vs paper #372 30 places worse paper 0.6054 ±0.0367 best at pub: Graph Neural Networks Inspired by Classical Iterative Algorithms (ICML 2021) best today: Steering Graph Neural Networks with Pinning Control (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.6054 ±0.0367 Δ at pub 0.0027 Δ today 0.0358
389	PairNorm GNN baseline	0.5892 ±0.0315	This paper

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 #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: Understanding convolution on graphs via energies (TMLR 2022) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.3744 ±0.0130 Δ today 0.0338
42	MLP Trad baseline actual #42 vs paper #158 116 places worse	0.4026 ±0.0108 best reported	actual #42 vs paper #158 116 places worse paper 0.3653 ±0.0070 best at pub: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited (NeurIPS 2022) best today: Heterophily-Aware Graph Attention Network (2023) paper 0.3653 ±0.0070 Δ at pub 0.0365 Δ today 0.0373
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: Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks (2022) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.3463 ±0.0122 Δ at pub 0.0175 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 ±0.0125 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.3487 ±0.0125 Δ at pub 0.0483
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: ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting (2022) best today: SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning (2023) paper 0.3735 ±0.0130 Δ at pub 0.0085 Δ today 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: 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 0.3754 ±0.0156 Δ today 0.0175
68	GraphSAGE GNN baseline actual #68 vs paper #258 190 places worse	0.3899 ±0.0085 best reported	actual #68 vs paper #258 190 places worse paper 0.3423 ±0.0099 best at pub: Deformable Graph Transformer (2022) best today: A Quasi-Wasserstein Loss for Learning Graph Neural Networks (WWW 2023) paper 0.3423 ±0.0099 Δ at pub 0.0101 Δ today 0.0476
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
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
121	G^2-GAT Hyb baseline	0.3730 ±0.0087	This paper
127	G^2-GraphSAGE Hyb baseline	0.3714 ±0.0101	This paper
132	G^2-GCN Hyb baseline	0.3709 ±0.0116	This paper
135	GCN GNN baseline actual #135 vs paper #408 273 places worse	0.3690 best reported	actual #135 vs paper #408 273 places worse paper 0.2732 ±0.0110 best at pub: Beyond Low-frequency Information in Graph Convolutional Networks (AAAI 2021) paper 0.2732 ±0.0110 Δ at pub 0.0958
153	F^2GAT GNN baseline	0.3665 ±0.0113	This paper
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: Deformable Graph Transformer (2022) best today: Towards Deep Attention in Graph Neural Networks: Problems and Remedies (ICML 2023) paper 0.3222 ±0.0234 Δ at pub 0.0357 Δ today 0.0426
180	LINKX GNN baseline	0.3610 ±0.0155	This paper
182	GAT GNN baseline actual #182 vs paper #406 224 places worse	0.3605 ±0.0035 best reported	actual #182 vs paper #406 224 places worse paper 0.2744 ±0.0089 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Hierarchical Graph Transformer with Adaptive Node Sampling (NeurIPS 2022) paper 0.2744 ±0.0089 Δ at pub 0.0816 Δ today 0.0861
183	ResGatedGCN GNN baseline	0.3602 ±0.0119	This paper
266	GIN code ↗ GNN global	0.3410 ±0.0030	What Can We Learn From MIMO Graph Convolutions? code ↗
408	PairNorm GNN baseline	0.2740 ±0.0124	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 GNN baseline actual #3 vs paper #206 203 places worse	0.8560 best reported	actual #3 vs paper #206 203 places worse paper 0.4836 ±0.0158 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs (KDD 2024) paper 0.4836 ±0.0158 Δ at pub 0.1814 Δ today 0.3724
43	G2-GraphSAGE baseline	0.7140 ±0.0238	This paper
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
52	GCN GNN baseline actual #52 vs paper #262 210 places worse	0.7033 best reported	actual #52 vs paper #262 210 places worse paper 0.3844 ±0.0192 best at pub: Non-Local Graph Neural Networks (2020) best today: Understanding Heterophily for Graph Neural Networks (ICML 2024) paper 0.3844 ±0.0192 Δ at pub 0.2916 Δ today 0.3189
64	LINKX GNN baseline	0.6842 ±0.0138	This paper
71	F2GAT GNN baseline	0.6781 ±0.0205	This paper
72	GPRGNN GNN baseline actual #72 vs paper #215 143 places worse	0.6748 ±0.0040 best reported	actual #72 vs paper #215 143 places worse paper 0.4658 ±0.0171 best at pub: Simplifying approach to Node Classification in Graph Neural Networks (2021) best today: $P^2$GNN: Two Prototype Sets to boost GNN Performance (2026) paper 0.4658 ±0.0171 Δ at pub 0.1989 Δ today 0.2090
99	G2-GAT baseline	0.6412 ±0.0196	This paper
103	GCNII GNN baseline	0.6386 ±0.0304	This paper
107	FAGCN GNN baseline actual #107 vs paper #164 57 places worse	0.6344 ±0.0205 best reported	actual #107 vs paper #164 57 places worse paper 0.5522 ±0.0319 best at pub: Non-Local Graph Neural Networks (2020) best today: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating (AAAI 2022) paper 0.5522 ±0.0319 Δ at pub 0.0648 Δ today 0.0822
108	SAGE code ↗ GNN global	0.6340 ±0.0300	Scale-aware Message Passing For Graph Node Classification code ↗
111	PairNorm GNN baseline	0.6274 ±0.0282	This paper
115	GraphSAGE GNN baseline actual #115 vs paper #143 28 places worse	0.6215 ±0.0042 best reported	actual #115 vs paper #143 28 places worse paper 0.5873 ±0.0168 best at pub: Simplifying approach to Node Classification in Graph Neural Networks (2021) best today: Hierarchical Graph Transformer with Adaptive Node Sampling (NeurIPS 2022) paper 0.5873 ±0.0168 Δ today 0.0342
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
129	MixHop GNN baseline	0.6050 ±0.0253	This paper
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
161	G2-GCN GNN baseline	0.5583 ±0.0288	This paper
169	MLP Trad baseline actual #169 vs paper #217 48 places worse	0.5429 best reported	actual #169 vs paper #217 48 places worse paper 0.4621 ±0.0299 best at pub: Block Modeling-Guided Graph Convolutional Neural Networks (AAAI 2021) best today: Understanding Heterophily for Graph Neural Networks (ICML 2024) paper 0.4621 ±0.0299 Δ at pub 0.0199 Δ today 0.0808
199	ResGatedGCN GNN baseline	0.4982 ±0.0271	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
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
30	G2-GraphSAGE 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 #235 189 places worse	0.6067 best reported	actual #46 vs paper #235 189 places worse paper 0.3152 ±0.0071 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) best today: Understanding Heterophily for Graph Neural Networks (ICML 2024) paper 0.3152 ±0.0071 Δ at pub 0.2418 Δ today 0.2915
67	GAT GNN baseline actual #67 vs paper #199 132 places worse	0.5630 ±0.0220 best reported	actual #67 vs paper #199 132 places worse paper 0.3677 ±0.0168 best at pub: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering (AAAI 2022) paper 0.3677 ±0.0168 Δ at pub 0.1953
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: Simplifying approach to Node Classification in Graph Neural Networks (2021) best today: Directed Homophily-Aware Graph Neural Network (2025) paper 0.3161 ±0.0124 Δ at pub 0.1742 Δ today 0.2274
88	PairNorm GNN baseline	0.5044 ±0.0204	This paper
100	F2GAT GNN baseline	0.4732 ±0.0243	This paper
105	G2-GAT baseline	0.4648 ±0.0141	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
128	GraphSAGE GNN baseline actual #128 vs paper #150 22 places worse	0.4378 ±0.0190 best reported	actual #128 vs paper #150 22 places worse paper 0.4161 ±0.0074 best at pub: Simplifying approach to Node Classification in Graph Neural Networks (2021) best today: UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.4161 ±0.0074 Δ today 0.0217
139	FAGCN GNN baseline actual #139 vs paper #139	0.4259 ±0.0079	actual #139 vs paper #139 paper 0.4259 ±0.0079 prev best: GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials (2022) Improvement within reported uncertainty; not highlighted. paper 0.4259 ±0.0079 Δ at pub 0.0016
167	G2-GCN GNN baseline	0.3962 ±0.0291	This paper
172	MLP Trad baseline actual #172 vs paper #243 71 places worse	0.3930 ±0.0079 best reported	actual #172 vs paper #243 71 places worse paper 0.2877 ±0.0156 best at pub: Block Modeling-Guided Graph Convolutional Neural Networks (AAAI 2021) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) paper 0.2877 ±0.0156 Δ at pub 0.0458 Δ today 0.1053
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	0.3815 ±0.0092	actual #179 vs paper #181 2 places worse paper 0.3815 ±0.0092 prev best: Simplifying approach to Node Classification in Graph Neural Networks (2021) Improvement within reported uncertainty; not highlighted. paper 0.3815 ±0.0092 Δ at pub 0.0001
192	ResGatedGCN GNN baseline	0.3760 ±0.0180	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 ↗
7	G^2-GraphSAGE Hyb baseline	0.6330 ±0.0184	This paper
13	LINKX GNN baseline	0.5600 ±0.0134	This paper
16	GloGNN GNN baseline actual #16 vs paper #16	0.5480 ±0.0030 best reported	actual #16 vs paper #16 paper 0.5468 ±0.0034 best at pub: Label-Wise Graph Convolutional Network for Heterophilic Graphs (2021) Difference within reported uncertainty; not counted as underperformance. paper 0.5468 ±0.0034 Δ at pub 0.0012
17	LINK Hyb baseline	0.5397 ±0.0018	This paper
19	MixHop GNN baseline actual #19 vs paper #19	0.5181 ±0.0017	actual #19 vs paper #19 paper 0.5181 ±0.0017 prev best: Label-Wise Graph Convolutional Network for Heterophilic Graphs (2021) paper 0.5181 ±0.0017 Δ at pub 0.0571
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 today: Uplifting Message Passing Neural Network with Graph Original Information (2022) paper 0.4605 ±0.0051 Δ today 0.0332
25	ACM-GCN GNN baseline actual #25 vs paper #25	0.4841 ±0.0030 best reported	actual #25 vs paper #25 paper 0.4737 ±0.0059 best today: Uplifting Message Passing Neural Network with Graph Original Information (2022) paper 0.4737 ±0.0059 Δ today 0.0104
26	GCNII GNN baseline	0.4721 ±0.0028	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
53	APPNP GNN baseline	0.3815 ±0.0026	This paper
56	MLP Trad baseline	0.3670 ±0.0021	This paper

snap-patents

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	FaberNet GNN global	0.7510 ±0.0003	HoloNets: Spectral Convolutions do extend to Directed Graphs
2	LargeScaleNet code ↗ Hyb global	0.7505 ±0.0005	Scale-aware Message Passing For Graph Node Classification code ↗
3	DirGNN code ↗ GNN global	0.7395 ±0.0005	Scale-aware Message Passing For Graph Node Classification code ↗
7	G^2-GraphSAGE Hyb baseline	0.6950 ±0.0039	This paper
10	GloGNN GNN baseline	0.6209 ±0.0027	This paper
11	LINKX GNN baseline	0.6195 ±0.0012	This paper
12	LINK Hyb baseline	0.6039 ±0.0007	This paper
14	ACM-GCN GNN baseline	0.5514 ±0.0016	This paper
15	MixHop GNN baseline	0.5216 ±0.0009	This paper
16	GCN GNN baseline actual #16 vs paper #22 6 places worse	0.5102 ±0.0006 best reported	actual #16 vs paper #22 6 places worse paper 0.4565 ±0.0004 best at pub: Non-Local Graph Neural Networks (2020) best today: Scale-aware Message Passing For Graph Node Classification (2024) paper 0.4565 ±0.0004 Δ at pub 0.0005 Δ today 0.0537
23	GAT GNN baseline actual #23 vs paper #23	0.4540 ±0.0040 best reported	actual #23 vs paper #23 paper 0.4537 ±0.0044 best at pub: Non-Local Graph Neural Networks (2020) Difference within reported uncertainty; not counted as underperformance. paper 0.4537 ±0.0044 Δ at pub 0.0003
28	GPR-GNN GNN baseline	0.4019 ±0.0003	This paper
30	GCNII GNN baseline	0.3788 ±0.0069	This paper
31	APPNP GNN baseline	0.3219 ±0.0007	This paper
32	MLP Trad baseline actual #32 vs paper #32	0.3134 ±0.0005	actual #32 vs paper #32 paper 0.3134 ±0.0005 prev best: Non-Local Graph Neural Networks (2020) best today: Understanding Heterophily for Graph Neural Networks (ICML 2024) Improvement within reported uncertainty; not highlighted. paper 0.3134 ±0.0005 Δ at pub 0.0004 Δ today 0.0016

SOTA performance (not significantly different from the best) 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