Distributed-Order Fractional Graph Operating Network

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

Abstract

We introduce the Distributed-order fRActional Graph Operating Network (DRAGON), a novel continuous Graph Neural Network (GNN) framework that incorporates distributed-order fractional calculus. Unlike traditional continuous GNNs that utilize integer-order or single fractional-order differential equations, DRAGON uses a learnable probability distribution over a range of real numbers for the derivative orders. By allowing a flexible and learnable superposition of multiple derivative orders, our framework captures complex graph feature updating dynamics beyond the reach of conventional models. We provide a comprehensive interpretation of our framework's capability to capture intricate dynamics through the lens of a non-Markovian graph random walk with node feature updating driven by an anomalous diffusion process over the graph. Furthermore, to highlight the versatility of the DRAGON framework, we conduct empirical evaluations across a range of graph learning tasks. The results consistently demonstrate superior performance when compared to traditional continuous GNN models. The implementation code is available at.

Benchmark Results

Tested on 9 datasets 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
94	F-GraphCON-nl GNN baseline	0.9410 ±0.0070	This paper
115	D-GraphCON-nl GNN baseline	0.9380 ±0.0080	This paper
124	D-GraphCON-l GNN baseline	0.9370 ±0.0040	This paper
168	D-GRAND-nl GNN baseline	0.9340 ±0.0050	This paper
178	F-GraphCON-l GNN baseline	0.9330 ±0.0100	This paper
210	D-GRAND-l GNN baseline	0.9310 ±0.0080	This paper
207	F-GRAND-nl GNN baseline	0.9310 ±0.0090	This paper
239	F-GRAND-l GNN baseline	0.9280 ±0.0060	This paper
298	GRAND-nl GNN baseline	0.9240 ±0.0080	This paper
310	GRAND-l GNN baseline	0.9230 ±0.0090	This paper
390	MLP code ↗ Trad global	0.9128 ±0.0063	Clarify Confused Nodes via Separated Learning code ↗
410	GraphCON-l GNN baseline	0.9080 ±0.0180	This paper
461	GIL GNN baseline	0.8960 ±0.0130	This paper
489	HGCN GNN baseline	0.8820 ±0.0140	This paper
505	GraphCON-nl GNN baseline	0.8550 ±0.0230	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: Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms (ICML 2024) best today: Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification (2026) paper 0.8260 ±0.0240 Δ at pub 0.0900 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: Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms (ICML 2024) 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 0.1440 Δ today 0.1598
8	SAGE code ↗ GNN global	0.9351 ±0.0006	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
244	D-GRAND-l GNN baseline	0.8730 ±0.0130	This paper
249	D-GRAND-nl GNN baseline	0.8710 ±0.0100	This paper
250	D-GraphCON-nl GNN baseline	0.8710 ±0.0100	This paper
258	D-GraphCON-l GNN baseline	0.8690 ±0.0100	This paper
284	F-GraphCON-l GNN baseline	0.8620 ±0.0080	This paper
314	GraphCON-l GNN baseline	0.8490 ±0.0050	This paper
320	MLP code ↗ Trad global	0.8463	GraphFM: A generalist graph transformer that learns transferable representations across diverse … code ↗
332	F-GRAND-l GNN baseline	0.8440 ±0.0150	This paper
348	F-GRAND-nl GNN baseline	0.8410 ±0.0090	This paper
360	GRAND-l GNN baseline	0.8370 ±0.0120	This paper
364	F-GraphCON-nl GNN baseline	0.8360 ±0.0220	This paper
394	GRAND-nl GNN baseline	0.8240 ±0.0210	This paper
426	HGCN GNN baseline	0.8060 ±0.0180	This paper
433	GraphCON-nl GNN baseline	0.7920 ±0.0110	This paper

Coauthor-Physics

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	GrokFormer code ↗ GT global	0.9831 ±0.0018	GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers code ↗
2	PolyFormer code ↗ GT global	0.9808 ±0.0027	GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers code ↗
3	SGFormer code ↗ GT global	0.9796 ±0.0081	GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers code ↗
6	GAT GNN baseline actual #6 vs paper #252 246 places worse	0.9782 ±0.0028 best reported	actual #6 vs paper #252 246 places worse paper 0.9250 ±0.0090 best at pub: Clarify Confused Nodes via Separated Learning (2023) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.9250 ±0.0090 Δ at pub 0.0413 Δ today 0.0532
9	GCN GNN baseline actual #9 vs paper #245 236 places worse	0.9774 ±0.0035 best reported	actual #9 vs paper #245 236 places worse paper 0.9280 ±0.0100 best at pub: SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling (WWW 2021) best today: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.9280 ±0.0100 Δ at pub 0.0370 Δ today 0.0494
17	SAGE code ↗ GNN global	0.9739 ±0.0018	Clarify Confused Nodes via Separated Learning code ↗
58	MLP code ↗ Trad global	0.9597 ±0.0007	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
172	D-GRAND-l GNN baseline	0.9460 ±0.0020	This paper
176	F-GRAND-l GNN baseline	0.9450 ±0.0040	This paper
185	D-GRAND-nl GNN baseline	0.9430 ±0.0060	This paper
186	D-GraphCON-l GNN baseline	0.9430 ±0.0050	This paper
195	F-GraphCON-l GNN baseline	0.9410 ±0.0050	This paper
199	D-GraphCON-nl GNN baseline	0.9400 ±0.0040	This paper
202	F-GRAND-nl GNN baseline	0.9390 ±0.0050	This paper
203	GraphCON-l GNN baseline	0.9390 ±0.0040	This paper
217	GRAND-l GNN baseline	0.9350 ±0.0090	This paper
234	GraphCON-nl GNN baseline	0.9310 ±0.0030	This paper
243	F-GraphCON-nl GNN baseline	0.9300 ±0.0060	This paper
267	GRAND-nl GNN baseline	0.9140 ±0.0130	This paper
271	HGCN GNN baseline	0.9080 ±0.0150	This paper

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 ↗
34	MLP Trad global	0.9230 ±0.0070	Design your own universe: a physics-informed agnostic method for enhancing graph neural networks
50	D-GREAD GNN baseline	0.9054 ±0.0325	This paper
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 #74 17 places worse	0.8973 ±0.0449 best reported	actual #57 vs paper #74 17 places worse paper 0.8892 ±0.0372 best at pub: 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 0.8892 ±0.0372 Δ at pub 0.0081
64	F-GREAD GNN baseline	0.8946 ±0.0374	This paper
107	D-GRAND GNN baseline	0.8649 ±0.0320	This paper

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
24	MLP Trad global	0.9136 ±0.0070	Node-oriented Spectral Filtering for Graph Neural Networks
26	D-GRAND GNN baseline	0.9000 ±0.0467	This paper
30	D-GREAD GNN baseline	0.8946 ±0.0426	This paper
52	GREAD GNN baseline actual #52 vs paper #60 8 places worse	0.8703 ±0.0495 best reported	actual #52 vs paper #60 8 places worse paper 0.8649 ±0.0715 best at pub: Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. (2024) best today: Graph Navier–Stokes Networks (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.8649 ±0.0715 Δ at pub 0.0054 Δ today 0.0054
55	F-GREAD GNN baseline	0.8689 ±0.0416	This paper
75	BLEND GNN baseline	0.8595 ±0.0682	This paper
95	Sheaf GNN baseline	0.8486 ±0.0471	This paper
112	GRAFF GNN baseline actual #112 vs paper #127 15 places worse	0.8405 ±0.0610 best reported	actual #112 vs paper #127 15 places worse paper 0.8324 ±0.0649 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 0.8324 ±0.0649 Δ at pub 0.0081 Δ today 0.0081
138	SAGE GNN global	0.8269	Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning

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 GNN baseline	0.9387 ±0.0041	This paper
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	0.7587 ±0.0043	This paper
108	FAGCN GNN baseline actual #108 vs paper #122 14 places worse	0.7571 ±0.0139 best reported	actual #108 vs paper #122 14 places worse paper 0.7053 ±0.0099 best at pub: NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification (2024) paper 0.7053 ±0.0099 Δ at pub 0.0518
114	GPR-GNN GNN baseline	0.7337 ±0.0068	This paper
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 baseline	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	0.6809 ±0.0029	This paper
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
149	TDE-GNN GNN baseline	0.6429 ±0.0058	This paper
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	0.6385 ±0.0049	This paper

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	0.5681 ±0.0090 best reported	actual #7 vs paper #182 175 places worse paper 0.4136 ±0.0047 best at pub: 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 0.1545
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
102	D-CDE GNN baseline	0.4943 ±0.0126	This paper
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	0.4632 ±0.0250	This paper
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 baseline	0.4505 ±0.0065	This paper
151	ACMP GNN baseline	0.4476 ±0.0052	This paper
154	CPGNN GNN baseline	0.4436 ±0.0035	This paper
162	GraphBel GNN baseline	0.4363 ±0.0042	This paper
186	TDE-GNN GNN baseline	0.4033 ±0.0137	This paper
194	Diag-NSD Hyb baseline	0.3796 ±0.0020	This paper
196	GloGNN GNN baseline	0.3728 ±0.0066	This paper

Minesweeper

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	BuNN code ↗ Hyb global	0.9899 ±0.0016	Bundle Neural Networks for message diffusion on graphs code ↗
2	DC-GNN GNN global	0.9850 ±0.0021	Differentiable Cluster Graph Neural Network
3	Tango -GPS global	0.9839 ±0.0054	TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
11	D-CDE GNN baseline	0.9647 ±0.0189	This paper
15	F-CDE GNN baseline	0.9604 ±0.0025	This paper
18	CDE GNN baseline	0.9550 ±0.0523	This paper
42	GraphSAGE code ↗ GNN global	0.9358 ±0.0005	Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax code ↗
76	GBK-GNN GNN baseline actual #76 vs paper #114 38 places worse	0.9085 ±0.0058 best reported	actual #76 vs paper #114 38 places worse paper 0.8356 ±0.0084 best at pub: Evolving Computation Graphs (ICML 2023) best today: TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows (2025) paper 0.8356 ±0.0084 Δ at pub 0.0729 Δ today 0.0729
81	ACM-GCN GNN baseline	0.9047 ±0.0057	This paper
85	H2GCN GNN baseline actual #85 vs paper #85	0.8995 ±0.0038	actual #85 vs paper #85 paper 0.8995 ±0.0038 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) Improvement within reported uncertainty; not highlighted. paper 0.8995 ±0.0038 Δ at pub 0.0024
91	FAGCN GNN baseline actual #91 vs paper #91	0.8969 ±0.0060	actual #91 vs paper #91 paper 0.8969 ±0.0060 prev best: Evolving Computation Graphs (ICML 2023) paper 0.8969 ±0.0060 Δ at pub 0.0152
94	Diag-NSD Hyb baseline	0.8959 ±0.0061	This paper
110	GPR-GNN GNN baseline actual #110 vs paper #115 5 places worse	0.8624 ±0.0061 best reported	actual #110 vs paper #115 5 places worse paper 0.8179 ±0.0098 best at pub: Evolving Computation Graphs (ICML 2023) best today: TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows (2025) paper 0.8179 ±0.0098 Δ at pub 0.0445 Δ today 0.0445
123	GRAND GNN baseline	0.7667 ±0.0098	This paper
124	GraphBel GNN baseline	0.7651 ±0.0103	This paper
125	ACMP GNN baseline	0.7615 ±0.0112	This paper
137	CPGNN GNN baseline actual #137 vs paper #137	0.7127 ±0.0114	actual #137 vs paper #137 paper 0.7127 ±0.0114 prev best: Evolving Computation Graphs (ICML 2023) paper 0.7127 ±0.0114 Δ at pub 0.1924
148	GloGNN GNN baseline actual #148 vs paper #148	0.6253 ±0.0134	actual #148 vs paper #148 paper 0.6253 ±0.0134 prev best: Graph Neural Networks for Graphs with Heterophily: A Survey (2022) paper 0.6253 ±0.0134 Δ at pub 0.1145
150	TDE-GNN GNN baseline	0.6115 ±0.0224	This paper
156	MLP Trad global	0.5099 ±0.0147	Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
157	ResNet Trad baseline actual #157 vs paper #157	0.5095 ±0.0112	actual #157 vs paper #157 paper 0.5095 ±0.0112 prev best: Evolving Computation Graphs (ICML 2023) Improvement within reported uncertainty; not highlighted. paper 0.5095 ±0.0112 Δ at pub 0.0006

Questions

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	NID_GAT code ↗ global	0.9703 ±0.0002	Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning code ↗
2	NID_GCN code ↗ global	0.9685 ±0.0010	Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning code ↗
3	UniGAP global	0.8421 ±0.0080	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node …
13	H2GCN GNN baseline actual #13 vs paper #120 107 places worse	0.7928 ±0.0080 best reported	actual #13 vs paper #120 107 places worse paper 0.6666 ±0.0184 best at pub: UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks (2024) paper 0.6666 ±0.0184 Δ at pub 0.1262
16	GCN GNN global	0.7902 ±0.0060	UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node …
43	FAGCN GNN baseline actual #43 vs paper #48 5 places worse	0.7724 ±0.0126 best reported	actual #43 vs paper #48 5 places worse paper 0.7704 ±0.0156 best at pub: Evolving Computation Graphs (ICML 2023) best today: TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.7704 ±0.0156 Δ at pub 0.0020 Δ today 0.0020
70	D-CDE GNN baseline	0.7553 ±0.0098	This paper
75	CDE GNN baseline	0.7517 ±0.0099	This paper
76	F-CDE GNN baseline	0.7517 ±0.0099	This paper
81	GBK-GNN GNN baseline actual #81 vs paper #88 7 places worse	0.7447 ±0.0086 best reported	actual #81 vs paper #88 7 places worse paper 0.7298 ±0.0105 best at pub: Evolving Computation Graphs (ICML 2023) best today: TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.7298 ±0.0105 Δ at pub 0.0149 Δ today 0.0149
86	GPR-GNN GNN baseline actual #86 vs paper #86	0.7341 ±0.0124	actual #86 vs paper #86 paper 0.7341 ±0.0124 prev best: Evolving Computation Graphs (ICML 2023) paper 0.7341 ±0.0124 Δ at pub 0.1793
93	ACMP GNN baseline	0.7118 ±0.0103	This paper
96	MLP code ↗ Trad global	0.7082 ±0.0010	Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax code ↗
98	GraphBel GNN baseline	0.7079 ±0.0099	This paper
99	GRAND GNN baseline	0.7067 ±0.0128	This paper
101	ResNet Trad baseline actual #101 vs paper #103 2 places worse	0.7034 ±0.0076 best reported	actual #101 vs paper #103 2 places worse paper 0.7010 ±0.0075 best at pub: Evolving Computation Graphs (ICML 2023) best today: Differentiable Cluster Graph Neural Network (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7010 ±0.0075 Δ at pub 0.0024 Δ today 0.0024
111	Diag-NSD Hyb baseline	0.6925 ±0.0115	This paper
113	TDE-GNN GNN baseline	0.6894 ±0.0169	This paper
119	GloGNN GNN baseline actual #119 vs paper #119	0.6715 ±0.0192	actual #119 vs paper #119 paper 0.6715 ±0.0192 prev best: Evolving Computation Graphs (ICML 2023) Improvement within reported uncertainty; not highlighted. paper 0.6715 ±0.0192 Δ at pub 0.0141
120	CPGNN GNN baseline actual #120 vs paper #120	0.6709 ±0.0263	actual #120 vs paper #120 paper 0.6709 ±0.0263 prev best: Evolving Computation Graphs (ICML 2023) Improvement within reported uncertainty; not highlighted. paper 0.6709 ±0.0263 Δ at pub 0.0113

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