Model-Driven Graph Contrastive Learning

Ali Azizpour, Nicolas Zilberstein, Santiago Segarra

Abstract

We propose MGCL, a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive learning by accounting for the data's underlying generative process. GCL has emerged as a powerful self-supervised framework for learning expressive node or graph representations without relying on annotated labels, which are often scarce in real-world data. By contrasting augmented views of graph data, GCL has demonstrated strong performance across various downstream tasks, such as node and graph classification. However, existing methods typically rely on manually designed or heuristic augmentation strategies that are not tailored to the underlying data distribution and operate at the individual graph level, ignoring similarities among graphs generated from the same model. Conversely, in our proposed approach, MGCL first estimates the graphon associated with the observed data and then defines a graphon-informed augmentation process, enabling data-adaptive and principled augmentations. Additionally, for graph-level tasks, MGCL clusters the dataset and estimates a graphon per group, enabling contrastive pairs to reflect shared semantics and structure. Extensive experiments on benchmark datasets demonstrate that MGCL achieves state-of-the-art performance, highlighting the advantages of incorporating generative models into GCL.

Benchmark Results

Tested on 7 datasets 22 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 code ↗ GNN global	0.9669 ±0.0014	Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification code ↗
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 #292 284 places worse	0.9632 ±0.0008 best reported	actual #8 vs paper #292 284 places worse paper 0.9242 ±0.0022 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 0.9242 ±0.0022 Δ at pub 0.0234 Δ today 0.0390
172	BGRL GNN baseline actual #172 vs paper #188 16 places worse	0.9337 ±0.0021 best reported	actual #172 vs paper #188 16 places worse paper 0.9324 ±0.0029 best at pub: Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning (AAAI 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.9324 ±0.0029 Δ at pub 0.0013
191	GCA GNN baseline actual #191 vs paper #244 53 places worse	0.9320 ±0.0060 best reported	actual #191 vs paper #244 53 places worse paper 0.9278 ±0.0017 best at pub: Unifying Graph Contrastive Learning with Flexible Contextual Scopes (2022) best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.9278 ±0.0017 Δ at pub 0.0042 Δ today 0.0042
203	GRACE GNN baseline actual #203 vs paper #263 60 places worse	0.9313 ±0.0017 best reported	actual #203 vs paper #263 60 places worse paper 0.9265 ±0.0028 best at pub: Learn Beneficial Noise as Graph Augmentation (ICML 2025) paper 0.9265 ±0.0028 Δ at pub 0.0048
206	MVGRL GNN baseline actual #206 vs paper #339 133 places worse	0.9310 ±0.0040 best reported	actual #206 vs paper #339 133 places worse paper 0.9201 ±0.0013 best at pub: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) paper 0.9201 ±0.0013 Δ at pub 0.0109
213	DGI GNN baseline actual #213 vs paper #375 162 places worse	0.9309 ±0.0008 best reported	actual #213 vs paper #375 162 places worse paper 0.9149 ±0.0025 best at pub: Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation (2024) paper 0.9149 ±0.0025 Δ at pub 0.0160
235	GBT GNN baseline actual #235 vs paper #266 31 places worse	0.9282 ±0.0040 best reported	actual #235 vs paper #266 31 places worse paper 0.9263 ±0.0044 best at pub: Str-GCL: Structural Commonsense Driven Graph Contrastive Learning (WWW 2025) Difference within reported uncertainty; not counted as underperformance. paper 0.9263 ±0.0044 Δ at pub 0.0019
246	MGCL GNN ★ proposed	0.9278 ±0.0023	This paper
320	GraphCL GNN baseline actual #320 vs paper #320	0.9222 ±0.0042	actual #320 vs paper #320 paper 0.9222 ±0.0042 prev best: PyG-SSL: A Graph Self-Supervised Learning Toolkit (2024) paper 0.9222 ±0.0042 Δ at pub 0.1052
390	MLP code ↗ Trad global	0.9128 ±0.0063	Clarify Confused Nodes via Separated Learning code ↗
457	Node2Vec Walk baseline actual #457 vs paper #458 1 place worse	0.8970 ±0.0010 best reported	actual #457 vs paper #458 1 place worse paper 0.8967 ±0.0012 best at pub: Learning Graph Augmentations to Learn Graph Representations (2022) best today: Multiplex Graph Contrastive Learning with Soft Negatives (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8967 ±0.0012 Δ at pub 0.0003 Δ today 0.0003
531	Raw features Trad baseline actual #531 vs paper #531	0.7999 ±0.0090	actual #531 vs paper #531 paper 0.7999 ±0.0090 prev best: Graph Contrastive Learning with Adaptive Augmentation (WWW 2020) paper 0.7999 ±0.0090 Δ at pub 0.0146

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 ↗
9	GCN GNN baseline actual #9 vs paper #90 81 places worse	0.9774 ±0.0035 best reported	actual #9 vs paper #90 81 places worse paper 0.9565 ±0.0016 best at pub: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers (ICML 2024) paper 0.9565 ±0.0016 Δ at pub 0.0209
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 ↗
63	GCA GNN baseline actual #63 vs paper #88 25 places worse	0.9590 ±0.0020 best reported	actual #63 vs paper #88 25 places worse paper 0.9568 ±0.0005 best at pub: Unifying Graph Contrastive Learning with Flexible Contextual Scopes (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.9568 ±0.0005 Δ at pub 0.0022
73	MGCL GNN ★ proposed	0.9580 ±0.0008	This paper
72	GraphCL GNN baseline	0.9580 ±0.0014	This paper
69	BGRL GNN baseline actual #69 vs paper #95 26 places worse	0.9580 ±0.0040 best reported	actual #69 vs paper #95 26 places worse paper 0.9563 ±0.0004 best at pub: Unifying Graph Contrastive Learning with Flexible Contextual Scopes (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.9563 ±0.0004 Δ at pub 0.0017
77	GRACE GNN baseline actual #77 vs paper #140 63 places worse	0.9574 ±0.0006 best reported	actual #77 vs paper #140 63 places worse paper 0.9526 ±0.0006 best at pub: Learn Beneficial Noise as Graph Augmentation (ICML 2025) paper 0.9526 ±0.0006 Δ at pub 0.0048
125	MVGRL GNN baseline actual #125 vs paper #134 9 places worse	0.9544 ±0.0027 best reported	actual #125 vs paper #134 9 places worse paper 0.9533 ±0.0003 best at pub: HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.9533 ±0.0003 Δ at pub 0.0011
149	GBT GNN baseline actual #149 vs paper #157 8 places worse	0.9520 ±0.0010 best reported	actual #149 vs paper #157 8 places worse paper 0.9507 ±0.0017 best at pub: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.9507 ±0.0017 Δ at pub 0.0013
167	DGI GNN baseline actual #167 vs paper #174 7 places worse	0.9489 ±0.0009 best reported	actual #167 vs paper #174 7 places worse paper 0.9451 ±0.0052 best at pub: Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition (WWW 2025) Difference within reported uncertainty; not counted as underperformance. paper 0.9451 ±0.0052 Δ at pub 0.0038
182	Raw features Trad baseline actual #182 vs paper #182	0.9432 ±0.0014	actual #182 vs paper #182 paper 0.9432 ±0.0014 prev best: Learning Graph Augmentations to Learn Graph Representations (2022) paper 0.9432 ±0.0014 Δ at pub 0.0072
268	Node2Vec Walk baseline actual #268 vs paper #268	0.9120 ±0.0010 best reported	actual #268 vs paper #268 paper 0.9119 ±0.0004 best at pub: Learning Graph Augmentations to Learn Graph Representations (2022) best today: Unifying Graph Contrastive Learning with Flexible Contextual Scopes (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.9119 ±0.0004 Δ at pub 0.0001 Δ today 0.0001

TU Dortmund

MUTAG

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	MSH-GNN GNN global	0.9910 ±0.0030	Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
2	ID-GNN+BEC Hyb global	0.9830 ±0.0360	Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature
3	SupCosine Hyb global	0.9830 ±0.0250	Supervised Contrastive Learning with Structure Inference for Graph Classification
39	GIN GNN global	0.9330 ±0.0290	ProtGNN: Towards Self-Explaining Graph Neural Networks
159	WL Trad baseline actual #159 vs paper #596 437 places worse	0.9040 ±0.0570 best reported	actual #159 vs paper #596 437 places worse paper 0.8072 ±0.0300 best at pub: How Powerful are $K$-hop Message Passing Graph Neural Networks (NeurIPS 2022) paper 0.8072 ±0.0300 Δ at pub 0.0968
199	MVGRL GNN baseline actual #199 vs paper #707 508 places worse	0.8993 ±0.0616 best reported	actual #199 vs paper #707 508 places worse paper 0.7540 ±0.0780 best at pub: Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization (KDD 2023) paper 0.7540 ±0.0780 Δ at pub 0.1453
227	MGCL GNN ★ proposed	0.8955 ±0.0108	This paper
257	InfoGraph GNN baseline actual #257 vs paper #272 15 places worse	0.8930 ±0.0514 best reported	actual #257 vs paper #272 15 places worse paper 0.8901 ±0.0113 best at pub: Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization (KDD 2023) Difference within reported uncertainty; not counted as underperformance. paper 0.8901 ±0.0113 Δ at pub 0.0029
351	JOAO GNN baseline actual #351 vs paper #370 19 places worse	0.8770 ±0.0080 best reported	actual #351 vs paper #370 19 places worse paper 0.8735 ±0.0102 best at pub: Graph Self-Supervised Learning: A Survey (2021) best today: Learning Graph Augmentations to Learn Graph Representations (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.8735 ±0.0102 Δ at pub 0.0035 Δ today 0.0035
354	GraphCL GNN baseline actual #354 vs paper #396 42 places worse	0.8766 ±0.0103 best reported	actual #354 vs paper #396 42 places worse paper 0.8680 ±0.0134 best at pub: Graph Masked Autoencoders with Transformers (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.8680 ±0.0134 Δ at pub 0.0086
365	DGK SVM baseline	0.8744 ±0.0272	This paper
403	MLP code ↗ Trad global	0.8660 ±0.0495	Breaking the Limits of Message Passing Graph Neural Networks code ↗
407	graph2vec Walk baseline actual #407 vs paper #517 110 places worse	0.8644 ±0.0125 best reported	actual #407 vs paper #517 110 places worse paper 0.8315 ±0.0925 best at pub: Graph Masked Autoencoders with Transformers (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.8315 ±0.0925 Δ at pub 0.0329
444	GL Trad baseline actual #444 vs paper #577 133 places worse	0.8520 ±0.0090 best reported	actual #444 vs paper #577 133 places worse paper 0.8166 ±0.0211 best at pub: On Valid Optimal Assignment Kernels and Applications to Graph Classification (NeurIPS 2016) paper 0.8166 ±0.0211 Δ at pub 0.0354
472	Sub2Vec Walk baseline actual #472 vs paper #786 314 places worse	0.8447 ±0.0037 best reported	actual #472 vs paper #786 314 places worse paper 0.6105 ±0.1580 best at pub: Graph Masked Autoencoders with Transformers (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.6105 ±0.1580 Δ at pub 0.2342
746	Node2Vec Walk baseline	0.7263 ±0.1020	This paper

NCI1

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	WL-MLP GT global	0.9954	1-WL Expressiveness Is (Almost) All You Need
2	GIN GNN global	0.9934	1-WL Expressiveness Is (Almost) All You Need
3	GCN GNN global	0.9727	1-WL Expressiveness Is (Almost) All You Need
12	WL Trad baseline actual #12 vs paper #223 211 places worse	0.8590 ±0.0010 best reported	actual #12 vs paper #223 211 places worse paper 0.8001 ±0.0050 best at pub: Propagation Kernels (2014) paper 0.8001 ±0.0050 Δ at pub 0.0589
104	GraphCL GNN baseline actual #104 vs paper #325 221 places worse	0.8250 ±0.0013 best reported	actual #104 vs paper #325 221 places worse paper 0.7787 ±0.0041 best at pub: Label-invariant Augmentation for Semi-Supervised Graph Classification (NeurIPS 2022) paper 0.7787 ±0.0041 Δ at pub 0.0463
131	GraphSAGE code ↗ GNN global	0.8200 ±0.0100	Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings code ↗
210	DGK SVM baseline	0.8031 ±0.0046	This paper
283	MGCL GNN ★ proposed	0.7866 ±0.0034	This paper
301	JOAO GNN baseline actual #301 vs paper #317 16 places worse	0.7840 ±0.0050 best reported	actual #301 vs paper #317 16 places worse paper 0.7807 ±0.0047 best at pub: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7807 ±0.0047 Δ at pub 0.0033
338	InfoGraph GNN baseline actual #338 vs paper #386 48 places worse	0.7750 ±0.0074 best reported	actual #338 vs paper #386 48 places worse paper 0.7620 ±0.0106 best at pub: Graph Masked Autoencoders with Transformers (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7620 ±0.0106 Δ at pub 0.0130
406	graph2vec Walk baseline actual #406 vs paper #446 40 places worse	0.7540 ±0.0120 best reported	actual #406 vs paper #446 40 places worse paper 0.7322 ±0.0181 best at pub: InfoGCL: Information-Aware Graph Contrastive Learning (NeurIPS 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.7322 ±0.0181 Δ at pub 0.0218
557	Sub2Vec Walk baseline actual #557 vs paper #575 18 places worse	0.5976 ±0.0035 best reported	actual #557 vs paper #575 18 places worse paper 0.5284 ±0.0147 best at pub: Graph Masked Autoencoders with Transformers (2022) paper 0.5284 ±0.0147 Δ at pub 0.0692
571	Node2Vec Walk baseline actual #571 vs paper #571	0.5490 ±0.0160 best reported	actual #571 vs paper #571 paper 0.5489 ±0.0161 best at pub: InfoGCL: Information-Aware Graph Contrastive Learning (NeurIPS 2021) best today: GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5489 ±0.0161 Δ at pub 0.0001 Δ today 0.0001

PROTEINS

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	MSH-GNN GNN global	0.9410 ±0.0330	Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
2	GRDL GNN global	0.8260 ±0.0120	Graph Classification via Reference Distribution Learning: Theory and Practice
3	GMN code ↗ Hyb global	0.8225	Memory-Based Graph Networks code ↗
32	GIN GNN global	0.7880 ±0.0410	Permutation-Invariant graph partitioning: How graph neural networks capture structural …
149	MLP Trad global	0.7600 ±0.0320	Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
178	DGK SVM baseline actual #178 vs paper #349 171 places worse	0.7568 ±0.0054 best reported	actual #178 vs paper #349 171 places worse paper 0.7330 ±0.0082 best at pub: Graph Capsule Convolutional Neural Networks (ICML 2018) best today: Hierarchical Graph Capsule Network (AAAI 2020) paper 0.7330 ±0.0082 Δ at pub 0.0238 Δ today 0.0238
190	WL Trad baseline actual #190 vs paper #369 179 places worse	0.7560 ±0.0040 best reported	actual #190 vs paper #369 179 places worse paper 0.7292 ±0.0056 best at pub: On Valid Optimal Assignment Kernels and Applications to Graph Classification (NeurIPS 2016) paper 0.7292 ±0.0056 Δ at pub 0.0268
265	GraphCL GNN baseline actual #265 vs paper #296 31 places worse	0.7489 ±0.0065 best reported	actual #265 vs paper #296 31 places worse paper 0.7439 ±0.0045 best at pub: Graph Masked Autoencoders with Transformers (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7439 ±0.0045 Δ at pub 0.0050
269	MGCL GNN ★ proposed	0.7485 ±0.0071	This paper
283	JOAO GNN baseline actual #283 vs paper #288 5 places worse	0.7460 ±0.0040 best reported	actual #283 vs paper #288 5 places worse paper 0.7455 ±0.0041 best at pub: GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling (2024) best today: Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition (WWW 2025) Difference within reported uncertainty; not counted as underperformance. paper 0.7455 ±0.0041 Δ at pub 0.0005 Δ today 0.0005
294	InfoGraph GNN baseline	0.7444 ±0.0031	This paper
350	graph2vec Walk baseline	0.7330 ±0.0205	This paper
474	Sub2Vec Walk baseline actual #474 vs paper #517 43 places worse	0.6731 ±0.0050 best reported	actual #474 vs paper #517 43 places worse paper 0.5303 ±0.0555 best at pub: Graph Masked Autoencoders with Transformers (2022) paper 0.5303 ±0.0555 Δ at pub 0.1428
514	Node2Vec Walk baseline actual #514 vs paper #514	0.5750 ±0.0360 best reported	actual #514 vs paper #514 paper 0.5749 ±0.0357 best at pub: GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5749 ±0.0357 Δ at pub 0.0001

COLLAB

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	WL-MLP GT global	0.9792	1-WL Expressiveness Is (Almost) All You Need
2	MSH-GNN GNN global	0.9640 ±0.0070	Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
3	CoCN code ↗ GNN global	0.8722 ±0.0013	Scalable Graph Compressed Convolutions code ↗
23	GCN code ↗ GNN global	0.8260 ±0.0220	Scalable Expressiveness through Preprocessed Graph Perturbations code ↗
80	GraphCL GNN baseline actual #80 vs paper #290 210 places worse	0.8108 ±0.0017 best reported	actual #80 vs paper #290 210 places worse paper 0.7136 ±0.0115 best at pub: Label-invariant Augmentation for Semi-Supervised Graph Classification (NeurIPS 2022) paper 0.7136 ±0.0115 Δ at pub 0.0972
146	InfoGraph GNN baseline actual #146 vs paper #295 149 places worse	0.7940 best reported	actual #146 vs paper #295 149 places worse paper 0.7065 ±0.0113 best at pub: CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2021) paper 0.7065 ±0.0113 Δ at pub 0.0875
151	MLP Trad global	0.7920 ±0.0240	Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
248	JOAO GNN baseline actual #248 vs paper #305 57 places worse	0.7535 ±0.0093 best reported	actual #248 vs paper #305 57 places worse paper 0.6950 ±0.0036 best at pub: Spectral Augmentation for Self-Supervised Learning on Graphs (ICLR 2022) paper 0.6950 ±0.0036 Δ at pub 0.0585
289	MGCL GNN ★ proposed	0.7144 ±0.0071	This paper

RDT-B

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	OEPG Hyb global	0.9630 ±0.0090	Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
2	MSH-GNN GNN global	0.9580 ±0.0090	Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
3	GNN-AK+ code ↗ GNN global	0.9480 ±0.0080	From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness code ↗
13	GIN GNN global	0.9240 ±0.0250	Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
23	GraphCL GNN baseline actual #23 vs paper #43 20 places worse	0.9169 ±0.0070 best reported	actual #23 vs paper #43 20 places worse paper 0.8953 ±0.0084 best at pub: Graph Contrastive Learning with Cohesive Subgraph Awareness (WWW 2024) paper 0.8953 ±0.0084 Δ at pub 0.0216
24	JOAO GNN baseline actual #24 vs paper #63 39 places worse	0.9166 ±0.0059 best reported	actual #24 vs paper #63 39 places worse paper 0.8529 ±0.0135 best at pub: Graph Contrastive Learning with Cohesive Subgraph Awareness (WWW 2024) paper 0.8529 ±0.0135 Δ at pub 0.0637
35	MGCL GNN ★ proposed	0.9025 ±0.0039	This paper
46	InfoGraph GNN baseline actual #46 vs paper #68 22 places worse	0.8939 ±0.0181 best reported	actual #46 vs paper #68 22 places worse paper 0.8250 ±0.0142 best at pub: Graph Contrastive Learning with Cohesive Subgraph Awareness (WWW 2024) paper 0.8250 ±0.0142 Δ at pub 0.0689
65	MVGRL GNN baseline actual #65 vs paper #68 3 places worse	0.8450 ±0.0060 best reported	actual #65 vs paper #68 3 places worse paper 0.8200 ±0.0110 best at pub: Graph Self-Supervised Learning: A Survey (2021) best today: ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning (2023) paper 0.8200 ±0.0110 Δ at pub 0.0250 Δ today 0.0250
73	DGK SVM baseline	0.7804 ±0.0039	This paper
75	GL Trad baseline	0.7734 ±0.0018	This paper
80	graph2vec Walk baseline actual #80 vs paper #80	0.7580 ±0.0100 best reported	actual #80 vs paper #80 paper 0.7578 ±0.0103 best at pub: Prototypical Graph Contrastive Learning (2021) best today: Self-Supervised Representation Learning via Latent Graph Prediction (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7578 ±0.0103 Δ at pub 0.0002 Δ today 0.0002
83	Sub2Vec Walk baseline actual #83 vs paper #83	0.7150 ±0.0040 best reported	actual #83 vs paper #83 paper 0.7148 ±0.0041 best at pub: Self-Supervised Representation Learning via Latent Graph Prediction (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7148 ±0.0041 Δ at pub 0.0002
85	WL Trad baseline	0.6882 ±0.0041	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