Graph Property Prediction On Ogbg Molpcba

평가 지표

Ext. data

Number of params

Test AP

Validation AP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Ext. data	Number of params	Test AP	Validation AP	Paper Title	Repository
GINE+ w/ APPNP	No	6147029	0.2979 ± 0.0030	0.3126 ± 0.0023	Graph convolutions that can finally model local structure	-
CRaWl	No	6115728	0.2986 ± 0.0025	0.3075 ± 0.0020	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing	-
GIN+virtual node	No	3374533	0.2703 ± 0.0023	0.2798 ± 0.0025	How Powerful are Graph Neural Networks?	-
GatedGCN+	No	6016860	0.2981 ± 0.0024	0.3011 ± 0.0037	Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence	-
GCN	No	565928	0.2020 ± 0.0024	0.2059 ± 0.0033	Semi-Supervised Classification with Graph Convolutional Networks	-
PHC-GNN	No	1690328	0.2947 ± 0.0026	0.3068 ± 0.0025	Parameterized Hypercomplex Graph Neural Networks for Graph Classification	-
GCN+virtual node+FLAG	No	2017028	0.2483 ± 0.0037	0.2556 ± 0.0040	Robust Optimization as Data Augmentation for Large-scale Graphs	-
HyperFusion	No	10887085	0.3204 ± 0.0001	0.3353 ± 0.0002	-	-
GIN-AK	No	3081029	0.2930 ± 0.0044	0.3047 ± 0.0007	From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness	-
TGT-Ag+TGT-At-DP	Yes	47000000	0.3167 ± 0.0031	-	Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers	-
Nested GIN+virtual node (ensemble)	No	44187480	0.3007 ± 0.0037	0.3059 ± 0.0056	Nested Graph Neural Networks	-
GCN+virtual node	No	2017028	0.2424 ± 0.0034	0.2495 ± 0.0042	Semi-Supervised Classification with Graph Convolutional Networks	-
Nested GIN+virtual node (ens)	-	-	0.3007 ± 0.0037	0.3059 ± 0.0056	Nested Graph Neural Networks	-
Graphormer	-	119529664	0.3140 ± 0.0032	0.3227 ± 0.0024	Do Transformers Really Perform Bad for Graph Representation?	-
PDF	No	3842048	0.3031 ± 0.0026	0.3115 ± 0.0020	Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering	-
DGN	No	6732696	0.2885 ± 0.0030	0.2970 ± 0.0021	Directional Graph Networks	-
GPS	No	9744496	0.2907	0.3015 ± 0.0038	Recipe for a General, Powerful, Scalable Graph Transformer	-
Graphormer (pre-trained on PCQM4M)	Yes	119529664	0.3140 ± 0.0032	0.3227 ± 0.0024	Do Transformers Really Perform Bad for Graph Representation?	-
PNA	No	6550839	0.2838 ± 0.0035	0.2926 ± 0.0026	Principal Neighbourhood Aggregation for Graph Nets	-
RandomGIN-vn+FLAG	No	5572026	0.2881 ± 0.0028	0.3035 ± 0.0047	RAN-GNNs: breaking the capacity limits of graph neural networks	-

0 of 36 row(s) selected.