graph-property-prediction-on-ogbg-molpcba

Graph Property Prediction

Results over time

Click legend items to toggle metrics. Hover points for model names.

Leaderboard

Paper	Code	Test AP	Ext. data	Validation AP	Number of params	ModelName	ReleaseDate
[]()		0.3204 ± 0.0001	No	0.3353 ± 0.0002	10887085	HyperFusino
[]()		0.3204 ± 0.0001	No	0.3353 ± 0.0002	10887085	HyperFusion
[]()		0.3167 ± 0.0034	Yes	0.3252 ± 0.0043	119529665	HIG(pre-trained on PCQM4M)
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers	✓ Link	0.3167 ± 0.0031	Yes		47000000	TGT-Ag+TGT-At-DP	2024-02-07
Do Transformers Really Perform Bad for Graph Representation?	✓ Link	0.3140 ± 0.0032		0.3227 ± 0.0024	119529664	Graphormer	2021-06-09
Do Transformers Really Perform Bad for Graph Representation?	✓ Link	0.3140 ± 0.0032	Yes	0.3227 ± 0.0024	119529664	Graphormer (pre-trained on PCQM4M)	2021-06-09
Next Level Message-Passing with Hierarchical Support Graphs	✓ Link	0.3129±0.0020				GatedGCN-HSG	2024-06-22
Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering	✓ Link	0.3031 ± 0.0026	No	0.3115 ± 0.0020	3842048	PDF	2023-05-10
[]()		0.3012 ± 0.0039	No	0.3151 ± 0.0047	5560960	PAS
Nested Graph Neural Networks	✓ Link	0.3007 ± 0.0037	No	0.3059 ± 0.0056	44187480	Nested GIN+virtual node (ensemble)	2021-10-25
Nested Graph Neural Networks	✓ Link	0.3007 ± 0.0037		0.3059 ± 0.0056		Nested GIN+virtual node (ens)	2021-10-25
[]()		0.2994 ± 0.0019	No	0.3094 ± 0.0023	5511680	GINE+bot
Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing	✓ Link	0.2986 ± 0.0025	No	0.3075 ± 0.0020	6115728	CRaWl	2021-02-17
Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence	✓ Link	0.2981 ± 0.0024	No	0.3011 ± 0.0037	6016860	GatedGCN+	2025-02-13
Graph convolutions that can finally model local structure	✓ Link	0.2979 ± 0.0030	No	0.3126 ± 0.0023	6147029	GINE+ w/ APPNP	2020-11-30
Global Self-Attention as a Replacement for Graph Convolution	✓ Link	0.2961 ± 0.0024				EGT	2021-08-07
Parameterized Hypercomplex Graph Neural Networks for Graph Classification	✓ Link	0.2947 ± 0.0026	No	0.3068 ± 0.0025	1690328	PHC-GNN	2021-03-30
From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness	✓ Link	0.2930 ± 0.0044	No	0.3047 ± 0.0007	3081029	GIN-AK	2021-10-07
Graph convolutions that can finally model local structure	✓ Link	0.2917 ± 0.0015	No	0.3065 ± 0.0030	6147029	GINE+ w/ virtual nodes	2020-11-30
Recipe for a General, Powerful, Scalable Graph Transformer	✓ Link	0.2907	No	0.3015 ± 0.0038	9744496	GPS	2022-05-25
Directional Graph Networks	✓ Link	0.2885 ± 0.0030	No	0.2970 ± 0.0021	6732696	DGN	2020-10-06
RAN-GNNs: breaking the capacity limits of graph neural networks		0.2881 ± 0.0028	No	0.3035 ± 0.0047	5572026	RandomGIN-vn+FLAG	2021-03-29
Robust Optimization as Data Augmentation for Large-scale Graphs	✓ Link	0.2842 ± 0.0043	No	0.2952 ± 0.0029	5550208	DeeperGCN+virtual node+FLAG	2020-10-19
Principal Neighbourhood Aggregation for Graph Nets	✓ Link	0.2838 ± 0.0035	No	0.2926 ± 0.0026	6550839	PNA	2020-04-12
Robust Optimization as Data Augmentation for Large-scale Graphs	✓ Link	0.2834 ± 0.0038	No	0.2912 ± 0.0026	3374533	GIN+virtual node+FLAG	2020-10-19
Nested Graph Neural Networks	✓ Link	0.2832 ± 0.0041		0.2915 ± 0.0035		Nested GIN+virtual node	2021-10-25
DeeperGCN: All You Need to Train Deeper GCNs	✓ Link	0.2781 ± 0.0038	No	0.2920 ± 0.0025	5550208	DeeperGCN+virtual node	2020-06-13
How Powerful are Graph Neural Networks?	✓ Link	0.2703 ± 0.0023	No	0.2798 ± 0.0025	3374533	GIN+virtual node	2018-10-01
Robust Optimization as Data Augmentation for Large-scale Graphs	✓ Link	0.2483 ± 0.0037	No	0.2556 ± 0.0040	2017028	GCN+virtual node+FLAG	2020-10-19
Semi-Supervised Classification with Graph Convolutional Networks	✓ Link	0.2424 ± 0.0034	No	0.2495 ± 0.0042	2017028	GCN+virtual node	2016-09-09
Robust Optimization as Data Augmentation for Large-scale Graphs	✓ Link	0.2395 ± 0.0040	No	0.2451 ± 0.0042	1923433	GIN+FLAG	2020-10-19
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering	✓ Link	0.2306 ± 0.0016	No	0.2372 ± 0.0018	1475003	ChebNet	2016-06-30
How Powerful are Graph Neural Networks?	✓ Link	0.2266 ± 0.0028	No	0.2305 ± 0.0027	1923433	GIN	2018-10-01
Robust Optimization as Data Augmentation for Large-scale Graphs	✓ Link	0.2116 ± 0.0017	No	0.2150 ± 0.0022	565928	GCN+FLAG	2020-10-19
[]()		0.2054 ± 0.0004	No	0.2226 ± 0.0002	29440000	MorganFP+Rand. Forest
Semi-Supervised Classification with Graph Convolutional Networks	✓ Link	0.2020 ± 0.0024	No	0.2059 ± 0.0033	565928	GCN	2016-09-09

OpenCodePapers

graph-property-prediction-on-ogbg-molpcba