16 Pre-training Molecular Graph Representation with 3D Geometry

Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang

Abstract

Molecular graph representation learning is a fundamental problem in modern drug and material discovery. Molecular graphs are typically modeled by their 2D topological structures, but it has been recently discovered that 3D geometric information plays a more vital role in predicting molecular functionalities. However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation. To cope with this challenge, we propose the Graph Multi-View Pre-training (GraphMVP) framework where self-supervised learning (SSL) is performed by leveraging the correspondence and consistency between 2D topological structures and 3D geometric views. GraphMVP effectively learns a 2D molecular graph encoder that is enhanced by richer and more discriminative 3D geometry. We further provide theoretical insights to justify the effectiveness of GraphMVP. Finally, comprehensive experiments show that GraphMVP can consistently outperform existing graph SSL methods. Code is available on GitHub.

Benchmark Results

Tested on 7 datasets 5 baseline values reported too low

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

MoleculeNet

Tox21

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	HIMP Hyb global	0.8740 ±0.0050	Graph convolutions that can finally model local structure
2	GINE w/ VN GNN global	0.8720 ±0.0030	Graph convolutions that can finally model local structure
3	NaiveGINe+ K=3 w/ VN GNN global	0.8700 ±0.0040	Graph convolutions that can finally model local structure
14	GCN GNN global	0.8400 ±0.0040	Graph convolutions that can finally model local structure
31	JOAO GNN baseline actual #31 vs paper #247 216 places worse	0.8230 ±0.0220 best reported	actual #31 vs paper #247 216 places worse paper 0.7440 ±0.0070 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7440 ±0.0070 Δ today 0.0790
35	EdgePred GNN baseline actual #35 vs paper #246 211 places worse	0.8180 ±0.0250 best reported	actual #35 vs paper #246 211 places worse paper 0.7450 ±0.0040 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7450 ±0.0040 Δ today 0.0730
46	ContextPred GNN baseline actual #46 vs paper #279 233 places worse	0.8060 ±0.0120 best reported	actual #46 vs paper #279 233 places worse paper 0.7330 ±0.0050 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7330 ±0.0050 Δ today 0.0730
47	GraphCL GNN baseline actual #47 vs paper #231 184 places worse	0.8050 ±0.0170 best reported	actual #47 vs paper #231 184 places worse paper 0.7500 ±0.0030 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7500 ±0.0030 Δ today 0.0550
61	GraphMVP ext data GNN ★ proposed actual #61 vs paper #246 185 places worse	0.7990 ±0.0180 best reported	actual #61 vs paper #246 185 places worse paper 0.7450 ±0.0040 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7450 ±0.0040 Δ today 0.0540
71	GraphLoG GNN baseline actual #71 vs paper #282 211 places worse	0.7960 ±0.0250 best reported	actual #71 vs paper #282 211 places worse paper 0.7300 ±0.0030 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7300 ±0.0030 Δ today 0.0660
81	InfoGraph GNN baseline actual #81 vs paper #282 201 places worse	0.7930 best reported	actual #81 vs paper #282 201 places worse paper 0.7300 ±0.0070 best at pub: GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction (AAAI 2021) paper 0.7300 ±0.0070 Δ at pub 0.0630
180	GPT-GNN LLM baseline actual #180 vs paper #211 31 places worse	0.7610 ±0.0040 best reported	actual #180 vs paper #211 31 places worse paper 0.7530 ±0.0050 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.7530 ±0.0050 Δ at pub 0.0080
184	GraphMVP-G ext data Hyb ★ proposed	0.7590 ±0.0050	This paper
220	G-Contextual GNN baseline	0.7520 ±0.0030	This paper
229	AttrMask GNN baseline actual #229 vs paper #259 30 places worse	0.7510 ±0.0090 best reported	actual #229 vs paper #259 30 places worse paper 0.7420 ±0.0080 best today: Motif-aware Attribute Masking for Molecular Graph Pre-training (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.7420 ±0.0080 Δ today 0.0090
236	-- baseline	0.7490 ±0.0080	This paper
249	GraphMVP-C ext data Hyb ★ proposed	0.7440 ±0.0020	This paper
280	G-Motif GNN baseline	0.7320 ±0.0080	This paper

BACE

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	ProtoMol Hyb global	0.9140 ±0.0030	ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
2	MMSG GNN global	0.9080 ±0.0050	ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
3	MemGNN code ↗ Hyb global	0.9070	Memory-Based Graph Networks code ↗
43	GIN code ↗ GNN global	0.8646 ±0.0081	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information … code ↗
98	GraphLoG GNN baseline actual #98 vs paper #206 108 places worse	0.8350 ±0.0120 best reported	actual #98 vs paper #206 108 places worse paper 0.7880 ±0.0070 best today: UGMAE: A Unified Framework for Graph Masked Autoencoders (2024) paper 0.7880 ±0.0070 Δ today 0.0470
100	JOAO GNN baseline actual #100 vs paper #261 161 places worse	0.8340 ±0.0330 best reported	actual #100 vs paper #261 161 places worse paper 0.7290 ±0.0200 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7290 ±0.0200 Δ today 0.1050
149	GraphMVP ext data GNN ★ proposed actual #149 vs paper #232 83 places worse	0.8120 ±0.0090 best reported	actual #149 vs paper #232 83 places worse paper 0.7680 ±0.0110 best today: Invariant-Based Diagnostics for Graph Benchmarks (2026) paper 0.7680 ±0.0110 Δ today 0.0440
150	GraphMVP-C ext data Hyb ★ proposed	0.8120 ±0.0090	This paper
176	EdgePred GNN baseline actual #176 vs paper #295 119 places worse	0.7990 ±0.0090 best reported	actual #176 vs paper #295 119 places worse paper 0.6460 ±0.0470 best today: Graph Self-Contrast Representation Learning (2023) paper 0.6460 ±0.0470 Δ today 0.1530
182	AttrMask GNN baseline actual #182 vs paper #226 44 places worse	0.7970 ±0.0033 best reported	actual #182 vs paper #226 44 places worse paper 0.7720 ±0.0140 best today: A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.7720 ±0.0140 Δ today 0.0250
186	ContextPred GNN baseline actual #186 vs paper #207 21 places worse	0.7960 ±0.0120 best reported	actual #186 vs paper #207 21 places worse paper 0.7860 ±0.0140 best today: Dual-perspective Cross Contrastive Learning in Graph Transformers (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7860 ±0.0140 Δ today 0.0100
192	GraphMVP-G ext data Hyb ★ proposed	0.7930 ±0.0150	This paper
196	G-Contextual GNN baseline	0.7920 ±0.0030	This paper
204	InfoGraph GNN baseline actual #204 vs paper #255 51 places worse	0.7890 ±0.0110 best reported	actual #204 vs paper #255 51 places worse paper 0.7390 ±0.0250 best today: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7390 ±0.0250 Δ today 0.0500
208	GPT-GNN LLM baseline actual #208 vs paper #225 17 places worse	0.7860 ±0.0290 best reported	actual #208 vs paper #225 17 places worse paper 0.7760 ±0.0050 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7760 ±0.0050 Δ at pub 0.0090 Δ today 0.0100
213	GraphCL GNN baseline actual #213 vs paper #286 73 places worse	0.7820 ±0.0120 best reported	actual #213 vs paper #286 73 places worse paper 0.6870 ±0.0780 best today: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.6870 ±0.0780 Δ today 0.0950
259	G-Motif GNN baseline	0.7340 ±0.0400	This paper
263	-- baseline	0.7260 ±0.0490	This paper

BBBP

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	MAGPrompt+ Hyb global	0.9432 ±0.0238	MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks
2	CamS-LLaMA LLM 100.0M global	0.9420	Multi-scale Graph Autoregressive Modeling: Molecular Property Prediction via Next Token …
3	SE(3)-I MPPH Hyb global	0.9400 ±0.0210	SE(3)-Invariant Multiparameter Persistent Homology for Chiral-Sensitive Molecular Property …
34	GIN code ↗ GNN global	0.8875 ±0.0049	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information … code ↗
36	GraphCL GNN baseline actual #36 vs paper #219 183 places worse	0.8870 ±0.0190 best reported	actual #36 vs paper #219 183 places worse paper 0.6750 ±0.0330 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6750 ±0.0330 Δ today 0.2120
39	JOAO GNN baseline actual #39 vs paper #253 214 places worse	0.8790 ±0.0200 best reported	actual #39 vs paper #253 214 places worse paper 0.6600 ±0.0060 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6600 ±0.0060 Δ today 0.2190
40	ContextPred GNN baseline actual #40 vs paper #118 78 places worse	0.8770 ±0.0260 best reported	actual #40 vs paper #118 78 places worse paper 0.7120 ±0.0090 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7120 ±0.0090 Δ today 0.1650
44	EdgePred GNN baseline actual #44 vs paper #278 234 places worse	0.8730 ±0.0160 best reported	actual #44 vs paper #278 234 places worse paper 0.6450 ±0.0310 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6450 ±0.0310 Δ today 0.2280
49	GraphMVP ext data GNN ★ proposed actual #49 vs paper #190 141 places worse	0.8600 ±0.0340 best reported	actual #49 vs paper #190 141 places worse paper 0.6850 ±0.0020 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6850 ±0.0020 Δ today 0.1750
54	GraphLoG GNN baseline actual #54 vs paper #205 151 places worse	0.8460 ±0.0080 best reported	actual #54 vs paper #205 151 places worse paper 0.6780 ±0.0170 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6780 ±0.0170 Δ today 0.1680
94	GraphMVP-C ext data Hyb ★ proposed	0.7240 ±0.0160	This paper
124	GraphMVP-G ext data Hyb ★ proposed	0.7080 ±0.0050	This paper
135	G-Contextual GNN baseline	0.7030 ±0.0160	This paper
136	G-Motif GNN baseline actual #136 vs paper #245 109 places worse	0.7030 ±0.0150 best reported	actual #136 vs paper #245 109 places worse paper 0.6640 ±0.0340 best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.6640 ±0.0340 Δ today 0.0390
141	AttrMask GNN baseline	0.7020 ±0.0050	This paper
173	InfoGraph GNN baseline	0.6920 ±0.0080	This paper
220	GPT-GNN LLM baseline actual #220 vs paper #278 58 places worse	0.6750 ±0.0130 best reported	actual #220 vs paper #278 58 places worse paper 0.6450 ±0.0110 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) paper 0.6450 ±0.0110 Δ at pub 0.0300
268	-- baseline	0.6540 ±0.0240	This paper

ClinTox

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	SE(3)-I MPPH Hyb global	0.9930 ±0.0040	SE(3)-Invariant Multiparameter Persistent Homology for Chiral-Sensitive Molecular Property …
2	KA-GCN code ↗ GNN global	0.9920 ±0.0050	A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the … code ↗
3	KA-GAT code ↗ GNN global	0.9910 ±0.0050	A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the … code ↗
19	GCN GNN global	0.9130 ±0.0170	OOD-GNN: Out-of-Distribution Generalized Graph Neural Network
40	AttrMask GNN baseline actual #40 vs paper #183 143 places worse	0.8770 ±0.0119 best reported	actual #40 vs paper #183 143 places worse paper 0.6860 ±0.0960 best today: A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.6860 ±0.0960 Δ today 0.1910
49	GraphMVP ext data GNN ★ proposed actual #49 vs paper #96 47 places worse	0.8650 ±0.0170 best reported	actual #49 vs paper #96 47 places worse paper 0.7900 ±0.0250 best today: SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning (NeurIPS 2024) paper 0.7900 ±0.0250 Δ today 0.0750
78	G-Motif GNN baseline actual #78 vs paper #106 28 places worse	0.8140 ±0.0220 best reported	actual #78 vs paper #106 28 places worse paper 0.7780 ±0.0200 best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7780 ±0.0200 Δ today 0.0360
79	JOAO GNN baseline actual #79 vs paper #195 116 places worse	0.8132 ±0.0249 best reported	actual #79 vs paper #195 116 places worse paper 0.6630 ±0.0390 best today: Graph Self-Contrast Representation Learning (2023) paper 0.6630 ±0.0390 Δ today 0.1502
96	GraphMVP-G ext data Hyb ★ proposed	0.7910 ±0.0280	This paper
97	GraphCL GNN baseline	0.7890 ±0.0420	This paper
103	GraphLoG GNN baseline actual #103 vs paper #216 113 places worse	0.7872 ±0.0258 best reported	actual #103 vs paper #216 113 places worse paper 0.6200 ±0.0180 best today: Graph Self-Contrast Representation Learning (2023) paper 0.6200 ±0.0180 Δ today 0.1672
106	InfoGraph GNN baseline actual #106 vs paper #128 22 places worse	0.7810 best reported	actual #106 vs paper #128 22 places worse paper 0.7510 ±0.0500 best at pub: GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction (AAAI 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.7510 ±0.0500 Δ at pub 0.0300
111	GraphMVP-C ext data Hyb ★ proposed	0.7750 ±0.0420	This paper
115	ContextPred GNN baseline actual #115 vs paper #142 27 places worse	0.7370 ±0.0400	actual #115 vs paper #142 27 places worse paper 0.7370 ±0.0400 prev best: MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph (KDD 2021) paper 0.7370 ±0.0400 Δ at pub 0.2310
131	GPT-GNN LLM baseline actual #131 vs paper #232 101 places worse	0.7490 ±0.0270 best reported	actual #131 vs paper #232 101 places worse paper 0.5780 ±0.0310 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) paper 0.5780 ±0.0310 Δ at pub 0.1710
191	G-Contextual GNN baseline actual #191 vs paper #222 31 places worse	0.6760 ±0.0290 best reported	actual #191 vs paper #222 31 places worse paper 0.5990 ±0.0820 best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5990 ±0.0820 Δ today 0.0770
192	EdgePred GNN baseline actual #192 vs paper #237 45 places worse	0.5580 ±0.0620	actual #192 vs paper #237 45 places worse paper 0.5580 ±0.0620 prev best: MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph (KDD 2021) Improvement within reported uncertainty; not highlighted. paper 0.5580 ±0.0620 Δ at pub 0.0540
226	-- baseline	0.5880 ±0.0550	This paper

SIDER

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	KA-GAT code ↗ GNN global	0.8470 ±0.0020	A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the … code ↗
2	KA-GCN code ↗ GNN global	0.8420 ±0.0010	A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the … code ↗
3	GraphKAN code ↗ GNN global	0.8370 ±0.0010	A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the … code ↗
66	GIN code ↗ GNN global	0.6403 ±0.0104	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information … code ↗
68	JOAO GNN baseline actual #68 vs paper #150 82 places worse	0.6400 ±0.0100 best reported	actual #68 vs paper #150 82 places worse paper 0.6070 ±0.0100 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6070 ±0.0100 Δ today 0.0330
70	GraphMVP ext data GNN ★ proposed actual #70 vs paper #99 29 places worse	0.6390 ±0.0120 best reported	actual #70 vs paper #99 29 places worse paper 0.6230 ±0.0160 best today: A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era (2026) Difference within reported uncertainty; not counted as underperformance. paper 0.6230 ±0.0160 Δ today 0.0160
71	GraphMVP-C ext data Hyb ★ proposed	0.6390 ±0.0120	This paper
103	ContextPred GNN baseline actual #103 vs paper #196 93 places worse	0.5930 ±0.0140	actual #103 vs paper #196 93 places worse paper 0.5930 ±0.0140 prev best: MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph (KDD 2021) paper 0.5930 ±0.0140 Δ at pub 0.0950
114	GraphCL GNN baseline actual #114 vs paper #178 64 places worse	0.6183 ±0.0060 best reported	actual #114 vs paper #178 64 places worse paper 0.6010 ±0.0130 best today: Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck (AAAI 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.6010 ±0.0130 Δ today 0.0173
123	GraphLoG GNN baseline actual #123 vs paper #220 97 places worse	0.6150 ±0.0130 best reported	actual #123 vs paper #220 97 places worse paper 0.5740 ±0.0230 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.5740 ±0.0230 Δ today 0.0410
134	AttrMask GNN baseline actual #134 vs paper #169 35 places worse	0.6120 ±0.0012 best reported	actual #134 vs paper #169 35 places worse paper 0.6040 ±0.0060 best today: A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.6040 ±0.0060 Δ today 0.0080
139	G-Contextual GNN baseline actual #139 vs paper #206 67 places worse	0.6110 ±0.0250 best reported	actual #139 vs paper #206 67 places worse paper 0.5840 ±0.0060 best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5840 ±0.0060 Δ today 0.0270
158	G-Motif GNN baseline	0.6060 ±0.0110	This paper
162	InfoGraph GNN baseline actual #162 vs paper #199 37 places worse	0.5920 ±0.0020	actual #162 vs paper #199 37 places worse paper 0.5920 ±0.0020 prev best: GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction (AAAI 2021) paper 0.5920 ±0.0020 Δ at pub 0.0070
170	EdgePred GNN baseline actual #170 vs paper #226 56 places worse	0.5670 ±0.0010	actual #170 vs paper #226 56 places worse paper 0.5670 ±0.0010 prev best: MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph (KDD 2021) best today: Community-Invariant Graph Contrastive Learning (ICML 2024) paper 0.5670 ±0.0010 Δ at pub 0.0650 Δ today 0.0370
177	GraphMVP-G ext data Hyb ★ proposed	0.6020 ±0.0110	This paper
197	GPT-GNN LLM baseline actual #197 vs paper #219 22 places worse	0.5930 ±0.0080 best reported	actual #197 vs paper #219 22 places worse paper 0.5750 ±0.0420 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.5750 ±0.0420 Δ at pub 0.0180
214	-- baseline	0.5800 ±0.0240	This paper

ToxCast

Global leaderboard →

#	Model	ROC-AUC ↑	Paper
1	GeomGCL GNN global	0.7630	GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
2	LiGhT DeepGPT ext data Hyb 0.4M global	0.7570 ±0.0110	Deep Prompt Tuning for Graph Transformers
3	CoMPT GT global	0.7550	GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
14	GCN GNN global	0.7350 ±0.0020	Graph convolutions that can finally model local structure
28	ContextPred GNN baseline actual #28 vs paper #167 139 places worse	0.7140 ±0.0180 best reported	actual #28 vs paper #167 139 places worse paper 0.6280 ±0.0030 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6280 ±0.0030 Δ today 0.0860
30	EdgePred GNN baseline actual #30 vs paper #194 164 places worse	0.7120 ±0.0110 best reported	actual #30 vs paper #194 164 places worse paper 0.6080 ±0.0050 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6080 ±0.0050 Δ today 0.1040
31	JOAO GNN baseline actual #31 vs paper #168 137 places worse	0.7110 ±0.0140 best reported	actual #31 vs paper #168 137 places worse paper 0.6270 ±0.0060 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6270 ±0.0060 Δ today 0.0840
35	InfoGraph GNN baseline actual #35 vs paper #184 149 places worse	0.7050 best reported	actual #35 vs paper #184 149 places worse paper 0.6200 ±0.0030 best at pub: GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction (AAAI 2021) paper 0.6200 ±0.0030 Δ at pub 0.0850
42	GraphCL GNN baseline actual #42 vs paper #167 125 places worse	0.6960 ±0.0230 best reported	actual #42 vs paper #167 125 places worse paper 0.6280 ±0.0020 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6280 ±0.0020 Δ today 0.0680
50	GraphMVP ext data GNN ★ proposed actual #50 vs paper #168 118 places worse	0.6890 ±0.0100 best reported	actual #50 vs paper #168 118 places worse paper 0.6270 ±0.0010 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6270 ±0.0010 Δ today 0.0620
64	GraphLoG GNN baseline actual #64 vs paper #181 117 places worse	0.6770 ±0.0190 best reported	actual #64 vs paper #181 117 places worse paper 0.6220 ±0.0040 best today: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6220 ±0.0040 Δ today 0.0550
150	AttrMask GNN baseline actual #150 vs paper #177 27 places worse	0.6330 ±0.0060 best reported	actual #150 vs paper #177 27 places worse paper 0.6250 ±0.0040 best today: Motif-aware Attribute Masking for Molecular Graph Pre-training (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.6250 ±0.0040 Δ today 0.0080
151	GPT-GNN LLM baseline actual #151 vs paper #181 30 places worse	0.6330 ±0.0030 best reported	actual #151 vs paper #181 30 places worse paper 0.6220 ±0.0010 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) best today: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks (ICLR 2024) paper 0.6220 ±0.0010 Δ at pub 0.0090 Δ today 0.0110
161	GraphMVP-G ext data Hyb ★ proposed	0.6310 ±0.0020	This paper
162	GraphMVP-C ext data Hyb ★ proposed	0.6310 ±0.0040	This paper
172	G-Contextual GNN baseline	0.6260 ±0.0030	This paper
173	G-Motif GNN baseline	0.6260 ±0.0050	This paper
186	-- baseline	0.6160 ±0.0120	This paper

ESOL

Global leaderboard →

#	Model	RMSE ↓	Paper
1	Graphormer-SPIS code ↗ GT global	0.4840 ±0.0050	On Structural Expressive Power of Graph Transformers code ↗
2	Graphormer-SPD code ↗ GT global	0.4920 ±0.0040	On Structural Expressive Power of Graph Transformers code ↗
3	conan-FGW global	0.5140 ±0.0190	Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
7	GCN code ↗ GNN global	0.5640 ±0.0150	On Structural Expressive Power of Graph Transformers code ↗
89	GraphMVP-C ext data Hyb ★ proposed	1.0290	This paper
92	GraphMVP-G ext data Hyb ★ proposed	1.0640	This paper
98	GraphMVP ext data GNN ★ proposed	1.0910	This paper
104	AM GNN baseline	1.1120	This paper
105	JOAO GNN baseline	1.1200	This paper
112	-- baseline	1.1780	This paper
115	CP GNN baseline	1.1960	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 Improved at pub — later paper surpassed this result Best today — OK at publication; today's leaderboard best is elsewhere