UGMAE: A Unified Framework for Graph Masked Autoencoders

Yijun Tian, Chuxu Zhang, Ziyi Kou, Zheyuan Liu, Xiangliang Zhang, N. Chawla

Abstract

Generative self-supervised learning on graphs, particularly graph masked autoencoders, has emerged as a popular learning paradigm and demonstrated its efficacy in handling non-Euclidean data. However, several remaining issues limit the capability of existing methods: 1) the disregard of uneven node significance in masking, 2) the underutilization of holistic graph information, 3) the ignorance of semantic knowledge in the representation space due to the exclusive use of reconstruction loss in the output space, and 4) the unstable reconstructions caused by the large volume of masked contents. In light of this, we propose UGMAE, a unified framework for graph masked autoencoders to address these issues from the perspectives of adaptivity, integrity, complementarity, and consistency. Specifically, we first develop an adaptive feature mask generator to account for the unique significance of nodes and sample informative masks (adaptivity). We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information and emphasize the topological proximity between neighbors (integrity). After that, we present a bootstrapping-based similarity module to encode the high-level semantic knowledge in the representation space, complementary to the low-level reconstruction in the output space (complementarity). Finally, we build a consistency assurance module to provide reconstruction objectives with extra stabilized consistency targets (consistency). Extensive experiments demonstrate that UGMAE outperforms both contrastive and generative state-of-the-art baselines on several tasks across multiple datasets.

Benchmark Results

Tested on 10 datasets 29 baseline values reported too low

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

Classic

PPI

Global leaderboard →

#	Model	F1 ↑	Paper
1	GAMLP(JK) code ↗ Hyb global	0.9982 ±0.0001	Graph Attention Multi-Layer Perceptron code ↗
2	GraphCON-GCN code ↗ Hyb global	0.9960	Graph-Coupled Oscillator Networks code ↗
3	GCNII GNN global	0.9953 ±0.0001	GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
21	GCN GNN baseline actual #21 vs paper #108 87 places worse	0.9850 best reported	actual #21 vs paper #108 87 places worse paper 0.7570 ±0.0010 best at pub: Graph-Coupled Oscillator Networks (ICML 2022) paper 0.7570 ±0.0010 Δ at pub 0.2280
57	GAT GNN baseline actual #57 vs paper #57	0.9732 ±0.0032 best reported	actual #57 vs paper #57 paper 0.9730 ±0.0020 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 0.9730 ±0.0020 Δ at pub 0.0002
92	GIN code ↗ GNN global	0.8724 ±0.0002	Search to aggregate neighborhood for graph neural network code ↗
111	UGMAE Hyb ★ proposed	0.7483 ±0.0033	This paper
113	GraphMAE2 GNN baseline	0.7451 ±0.0036	This paper
114	GraphMAE GNN baseline	0.7450 ±0.0029	This paper
117	BGRL GNN baseline	0.7363 ±0.0016	This paper
119	CCA-SSG GNN baseline	0.7334 ±0.0017	This paper
126	GRACE GNN baseline	0.6971 ±0.0017	This paper
148	DGI GNN baseline	0.6380 ±0.0020	This paper
173	MLP Trad global	0.4620	Graph Neural Networks Gone Hogwild

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 baseline actual #39 vs paper #237 198 places worse	0.9330 ±0.0290 best reported	actual #39 vs paper #237 198 places worse paper 0.8940 ±0.0560 best at pub: ProtGNN: Towards Self-Explaining Graph Neural Networks (AAAI 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.8940 ±0.0560 Δ at pub 0.0390
63	GCN GNN global	0.9220 ±0.0440	Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature
105	InfoGCL GNN baseline	0.9120 ±0.0130	This paper
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 #213 14 places worse	0.8993 ±0.0616 best reported	actual #199 vs paper #213 14 places worse paper 0.8970 ±0.0110 best at pub: Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization (KDD 2023) Difference within reported uncertainty; not counted as underperformance. paper 0.8970 ±0.0110 Δ at pub 0.0023
226	GraphMAE2 GNN baseline actual #226 vs paper #402 176 places worse	0.8960 ±0.0030 best reported	actual #226 vs paper #402 176 places worse paper 0.8663 ±0.0133 best today: CORE: Contrastive Masked Feature Reconstruction on Graphs (2025) paper 0.8663 ±0.0133 Δ today 0.0297
239	DiffPool GNN baseline actual #239 vs paper #447 208 places worse	0.8940 ±0.0460 best reported	actual #239 vs paper #447 208 places worse paper 0.8500 ±0.1030 best at pub: Total Variation Graph Neural Networks (ICML 2022) best today: Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8500 ±0.1030 Δ at pub 0.0140 Δ today 0.0440
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
258	GraphMAE GNN baseline actual #258 vs paper #326 68 places worse	0.8930 ±0.0110 best reported	actual #258 vs paper #326 68 places worse paper 0.8819 ±0.0126 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) best today: Revisiting Graph Autoencoders as Implicit Contrastive Learners (KDD 2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8819 ±0.0126 Δ today 0.0111
324	UGMAE Hyb ★ proposed	0.8826 ±0.0119	This paper
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

NCI1

Global leaderboard →

#	Model	Accuracy ↑	Paper
1	WL-MLP GT global	0.9954	1-WL Expressiveness Is (Almost) All You Need
2	GIN GNN baseline actual #2 vs paper #91 89 places worse	0.9934 best reported	actual #2 vs paper #91 89 places worse paper 0.8270 ±0.0170 best at pub: 1-WL Expressiveness Is (Almost) All You Need (2022) paper 0.8270 ±0.0170 Δ at pub 0.1664
3	GCN GNN global	0.9727	1-WL Expressiveness Is (Almost) All You Need
12	WL Trad baseline actual #12 vs paper #209 197 places worse	0.8590 ±0.0010 best reported	actual #12 vs paper #209 197 places worse paper 0.8031 ±0.0046 best at pub: Propagation Kernels (2014) paper 0.8031 ±0.0046 Δ at pub 0.0559
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
116	GraphMAE2 GNN baseline actual #116 vs paper #293 177 places worse	0.8230 ±0.0090 best reported	actual #116 vs paper #293 177 places worse paper 0.7856 ±0.0026 best today: Revisiting Graph Autoencoders as Implicit Contrastive Learners (KDD 2024) paper 0.7856 ±0.0026 Δ today 0.0374
131	GraphSAGE code ↗ GNN global	0.8200 ±0.0100	Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings code ↗
199	UGMAE Hyb ★ proposed	0.8046 ±0.0017	This paper
200	GraphMAE GNN baseline actual #200 vs paper #202 2 places worse	0.8042 ±0.0035 best reported	actual #200 vs paper #202 2 places worse paper 0.8040 ±0.0030 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) best today: Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.8040 ±0.0030 Δ today 0.0002
210	DGK SVM baseline	0.8031 ±0.0046	This paper
215	InfoGCL GNN baseline	0.8020 ±0.0060	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

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 ↗
10	GraphMAE2 GNN baseline actual #10 vs paper #190 180 places worse	0.8410 ±0.0030 best reported	actual #10 vs paper #190 180 places worse paper 0.7759 ±0.0022 best today: CORE: Contrastive Masked Feature Reconstruction on Graphs (2025) paper 0.7759 ±0.0022 Δ today 0.0651
22	GraphMAE GNN baseline actual #22 vs paper #109 87 places worse	0.8270 ±0.0100 best reported	actual #22 vs paper #109 87 places worse paper 0.8032 ±0.0046 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) best today: Revisiting Graph Autoencoders as Implicit Contrastive Learners (KDD 2024) paper 0.8032 ±0.0046 Δ today 0.0238
23	GCN code ↗ GNN global	0.8260 ±0.0220	Scalable Expressiveness through Preprocessed Graph Perturbations code ↗
30	GIN GNN baseline actual #30 vs paper #111 81 places worse	0.8220 ±0.0210 best reported	actual #30 vs paper #111 81 places worse paper 0.8020 ±0.0190 best at pub: On the Equivalence between Graph Isomorphism Testing and Function Approximation with GNNs (NeurIPS 2019) best today: Scalable Expressiveness through Preprocessed Graph Perturbations (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.8020 ±0.0190 Δ today 0.0200
33	DiffPool GNN baseline actual #33 vs paper #161 128 places worse	0.8213 ±0.0043 best reported	actual #33 vs paper #161 128 places worse paper 0.7890 ±0.0230 best at pub: CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2021) best today: Scalable Graph Compressed Convolutions (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.7890 ±0.0230 Δ at pub 0.0037 Δ today 0.0323
45	UGMAE Hyb ★ proposed	0.8166 ±0.0012	This paper
75	GCC GNN baseline actual #75 vs paper #161 86 places worse	0.8110 best reported	actual #75 vs paper #161 86 places worse paper 0.7890 best at pub: Graph Self-Supervised Learning: A Survey (2021) paper 0.7890 Δ at pub 0.0220
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
126	InfoGCL GNN baseline actual #126 vs paper #126	0.8001 ±0.0132 best reported	actual #126 vs paper #126 paper 0.8000 ±0.0130 best at pub: InfoGCL: Information-Aware Graph Contrastive Learning (NeurIPS 2021) best today: Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations (2025) Difference within reported uncertainty; not counted as underperformance. paper 0.8000 ±0.0130 Δ today 0.0001
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

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 #231 200 places worse	0.8230 ±0.0220 best reported	actual #31 vs paper #231 200 places worse paper 0.7500 ±0.0030 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7500 ±0.0030 Δ at pub 0.0730
37	Infomax GNN baseline actual #37 vs paper #211 174 places worse	0.8160 ±0.0210 best reported	actual #37 vs paper #211 174 places worse paper 0.7530 ±0.0050 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7530 ±0.0050 Δ at pub 0.0630
46	ContextPred ext data GNN baseline actual #46 vs paper #193 147 places worse	0.8060 ±0.0120 best reported	actual #46 vs paper #193 147 places worse paper 0.7570 ±0.0070 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7570 ±0.0070 Δ at pub 0.0490
47	GraphCL GNN baseline actual #47 vs paper #265 218 places worse	0.8050 ±0.0170 best reported	actual #47 vs paper #265 218 places worse paper 0.7390 ±0.0070 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7390 ±0.0070 Δ at pub 0.0660
71	GraphLoG GNN baseline actual #71 vs paper #193 122 places worse	0.7960 ±0.0250 best reported	actual #71 vs paper #193 122 places worse paper 0.7570 ±0.0050 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7570 ±0.0050 Δ at pub 0.0390
163	AttrMasking ext data GNN baseline	0.7670 ±0.0040	This paper
176	UGMAE Hyb ★ proposed	0.7630 ±0.0030	This paper
190	GraphMAE2 GNN baseline	0.7580 ±0.0090	This paper
202	GraphMAE GNN baseline	0.7550 ±0.0060	This paper
255	No-pretrain GNN baseline	0.7430 ±0.0050	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 ↗
67	UGMAE Hyb ★ proposed	0.8530 ±0.0100	This paper
98	GraphLoG GNN baseline	0.8350 ±0.0120	This paper
100	JOAO GNN baseline actual #100 vs paper #226 126 places worse	0.8340 ±0.0330 best reported	actual #100 vs paper #226 126 places worse paper 0.7730 ±0.0050 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7730 ±0.0050 Δ at pub 0.0610
105	GraphMAE GNN baseline	0.8310 ±0.0090	This paper
151	GraphMAE2 GNN baseline	0.8120 ±0.0130	This paper
186	ContextPred ext data GNN baseline	0.7960 ±0.0120	This paper
191	AttrMasking ext data GNN baseline	0.7930 ±0.0160	This paper
213	GraphCL GNN baseline actual #213 vs paper #248 35 places worse	0.7820 ±0.0120 best reported	actual #213 vs paper #248 35 places worse paper 0.7540 ±0.0140 best at pub: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) paper 0.7540 ±0.0140 Δ at pub 0.0280
225	Infomax GNN baseline actual #225 vs paper #243 18 places worse	0.7590 ±0.0160	actual #225 vs paper #243 18 places worse paper 0.7590 ±0.0160 prev best: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) Improvement within reported uncertainty; not highlighted. paper 0.7590 ±0.0160 Δ at pub 0.0030
231	No-pretrain GNN baseline actual #231 vs paper #283 52 places worse	0.7700 ±0.0210 best reported	actual #231 vs paper #283 52 places worse paper 0.7000 ±0.0250 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) best today: Dual-perspective Cross Contrastive Learning in Graph Transformers (2024) paper 0.7000 ±0.0250 Δ today 0.0700

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 #158 122 places worse	0.8870 ±0.0190 best reported	actual #36 vs paper #158 122 places worse paper 0.6970 ±0.0070 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6970 ±0.0070 Δ at pub 0.1900
39	JOAO GNN baseline actual #39 vs paper #140 101 places worse	0.8790 ±0.0200 best reported	actual #39 vs paper #140 101 places worse paper 0.7020 ±0.0100 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7020 ±0.0100 Δ at pub 0.1770
40	ContextPred ext data GNN baseline actual #40 vs paper #279 239 places worse	0.8770 ±0.0260 best reported	actual #40 vs paper #279 239 places worse paper 0.6430 ±0.0280 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6430 ±0.0280 Δ at pub 0.2340
54	GraphLoG GNN baseline actual #54 vs paper #90 36 places worse	0.8460 ±0.0080 best reported	actual #54 vs paper #90 36 places worse paper 0.7250 ±0.0080 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.7250 ±0.0080 Δ at pub 0.1210
55	Infomax GNN baseline actual #55 vs paper #183 128 places worse	0.8400 ±0.0260 best reported	actual #55 vs paper #183 128 places worse paper 0.6880 ±0.0080 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6880 ±0.0080 Δ at pub 0.1520
87	UGMAE Hyb ★ proposed	0.7280 ±0.0040	This paper
101	GraphMAE GNN baseline	0.7200 ±0.0060	This paper
116	GraphMAE2 GNN baseline	0.7150 ±0.0150	This paper
230	AttrMasking ext data GNN baseline actual #230 vs paper #279 49 places worse	0.6712 ±0.0045 best reported	actual #230 vs paper #279 49 places worse paper 0.6430 ±0.0280 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) 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 0.6430 ±0.0280 Δ today 0.0282
265	No-pretrain GNN baseline	0.6550 ±0.0180	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
69	UGMAE Hyb ★ proposed	0.8240 ±0.0130	This paper
71	GraphMAE GNN baseline	0.8230 ±0.0120	This paper
79	JOAO GNN baseline actual #79 vs paper #79	0.8132 ±0.0249 best reported	actual #79 vs paper #79 paper 0.8130 ±0.0250 best at pub: Graph Self-Contrast Representation Learning (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.8130 ±0.0250 Δ at pub 0.0002
97	GraphCL GNN baseline actual #97 vs paper #120 23 places worse	0.7890 ±0.0420 best reported	actual #97 vs paper #120 23 places worse paper 0.7600 ±0.0270 best at pub: 16 Pre-training Molecular Graph Representation with 3D Geometry (ICLR 2021) best today: Improving Molecular Pretraining with Complementary Featurizations (2022) Difference within reported uncertainty; not counted as underperformance. paper 0.7600 ±0.0270 Δ at pub 0.0290 Δ today 0.0290
101	GraphMAE2 GNN baseline	0.7890 ±0.0280	This paper
103	GraphLoG GNN baseline actual #103 vs paper #116 13 places worse	0.7872 ±0.0258 best reported	actual #103 vs paper #116 13 places worse paper 0.7670 ±0.0330 best at pub: Let Invariant Rationale Discovery Inspire Graph Contrastive Learning (ICML 2022) best today: Graph Self-Contrast Representation Learning (2023) Difference within reported uncertainty; not counted as underperformance. paper 0.7670 ±0.0330 Δ at pub 0.0202 Δ today 0.0202
115	ContextPred ext data GNN baseline actual #115 vs paper #197 82 places worse	0.7720 ±0.0088 best reported	actual #115 vs paper #197 82 places worse paper 0.6590 ±0.0380 best at pub: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining (ICML 2023) best today: A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery (2025) paper 0.6590 ±0.0380 Δ at pub 0.1130 Δ today 0.1130
151	Infomax GNN baseline actual #151 vs paper #174 23 places worse	0.7300 ±0.0320 best reported	actual #151 vs paper #174 23 places worse paper 0.6990 ±0.0300 best at pub: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (NeurIPS 2021) Difference within reported uncertainty; not counted as underperformance. paper 0.6990 ±0.0300 Δ at pub 0.0310
162	AttrMasking ext data GNN baseline	0.7180 ±0.0410	This paper
205	No-pretrain GNN baseline actual #205 vs paper #228 23 places worse	0.6440 ±0.0420 best reported	actual #205 vs paper #228 23 places worse paper 0.5820 ±0.0280 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) best today: Dual-perspective Cross Contrastive Learning in Graph Transformers (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5820 ±0.0280 Δ today 0.0620

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 ↗
56	UGMAE Hyb ★ proposed	0.6460 ±0.0040	This paper
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 #182 114 places worse	0.6400 ±0.0100 best reported	actual #68 vs paper #182 114 places worse paper 0.6000 ±0.0080 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6000 ±0.0080 Δ at pub 0.0400
103	ContextPred ext data GNN baseline actual #103 vs paper #144 41 places worse	0.6220 ±0.0059 best reported	actual #103 vs paper #144 41 places worse paper 0.6090 ±0.0060 best at pub: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining (ICML 2023) best today: A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery (2025) paper 0.6090 ±0.0060 Δ at pub 0.0130 Δ today 0.0130
114	GraphCL GNN baseline actual #114 vs paper #162 48 places worse	0.6183 ±0.0060 best reported	actual #114 vs paper #162 48 places worse paper 0.6050 ±0.0090 best at pub: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (ICML 2022) 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 0.6050 ±0.0090 Δ at pub 0.0030 Δ today 0.0133
120	Infomax GNN baseline actual #120 vs paper #206 86 places worse	0.6160 ±0.0240 best reported	actual #120 vs paper #206 86 places worse paper 0.5840 ±0.0080 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.5840 ±0.0080 Δ at pub 0.0320
123	GraphLoG GNN baseline actual #123 vs paper #133 10 places worse	0.6150 ±0.0130 best reported	actual #123 vs paper #133 10 places worse paper 0.6120 ±0.0110 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) Difference within reported uncertainty; not counted as underperformance. paper 0.6120 ±0.0110 Δ at pub 0.0030
133	AttrMasking ext data GNN baseline actual #133 vs paper #141 8 places worse	0.6121 ±0.0065 best reported	actual #133 vs paper #141 8 places worse paper 0.6100 ±0.0070 best at pub: GraphMAE: Self-Supervised Masked Graph Autoencoders (KDD 2022) 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 0.6100 ±0.0070 Δ today 0.0021
175	GraphMAE GNN baseline	0.6030 ±0.0110	This paper
193	GraphMAE2 GNN baseline	0.5970 ±0.0060	This paper
213	No-pretrain GNN baseline actual #213 vs paper #223 10 places worse	0.5810 ±0.0100 best reported	actual #213 vs paper #223 10 places worse paper 0.5720 ±0.0070 best today: Dual-perspective Cross Contrastive Learning in Graph Transformers (2024) Difference within reported uncertainty; not counted as underperformance. paper 0.5720 ±0.0070 Δ today 0.0090

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 ext data GNN baseline actual #28 vs paper #131 103 places worse	0.7140 ±0.0180 best reported	actual #28 vs paper #131 103 places worse paper 0.6390 ±0.0060 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6390 ±0.0060 Δ at pub 0.0750
31	JOAO GNN baseline actual #31 vs paper #165 134 places worse	0.7110 ±0.0140 best reported	actual #31 vs paper #165 134 places worse paper 0.6290 ±0.0050 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6290 ±0.0050 Δ at pub 0.0820
42	GraphCL GNN baseline actual #42 vs paper #178 136 places worse	0.6960 ±0.0230 best reported	actual #42 vs paper #178 136 places worse paper 0.6240 ±0.0060 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6240 ±0.0060 Δ at pub 0.0720
49	Infomax GNN baseline actual #49 vs paper #168 119 places worse	0.6900 ±0.0120 best reported	actual #49 vs paper #168 119 places worse paper 0.6270 ±0.0040 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6270 ±0.0040 Δ at pub 0.0630
64	GraphLoG GNN baseline actual #64 vs paper #137 73 places worse	0.6770 ±0.0190 best reported	actual #64 vs paper #137 73 places worse paper 0.6350 ±0.0070 best at pub: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction (KDD 2022) paper 0.6350 ±0.0070 Δ at pub 0.0420
97	UGMAE Hyb ★ proposed	0.6560 ±0.0030	This paper
102	GraphMAE2 GNN baseline	0.6530 ±0.0080	This paper
126	AttrMasking ext data GNN baseline	0.6420 ±0.0050	This paper
128	GraphMAE GNN baseline	0.6410 ±0.0030	This paper
152	No-pretrain GNN baseline	0.6330 ±0.0150	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 today — OK at publication; today's leaderboard best is elsewhere