Graph Property Prediction On Ogbg Molhiv

평가 지표

Test ROC-AUC

Validation ROC-AUC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Test ROC-AUC	Validation ROC-AUC	Paper Title	Repository
Nested GIN+virtual node (ens)	0.7986 ± 0.0105	0.8080 ± 0.0278	Nested Graph Neural Networks
EGT	0.806 ± 0.0065	-	Global Self-Attention as a Replacement for Graph Convolution
GPTrans-B	0.8126 ± 0.0032	-	Graph Propagation Transformer for Graph Representation Learning
GIN	0.7825 ± 0.0121	0.8009 ± 0.0078	-	-
Molecular FP + Random Forest	0.8208 ± 0.0037	0.8036 ± 0.0059	-	-
GatedGCN+	0.8040 ± 0.0164	0.8329 ± 0.0158	Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence
GCN+FLAG	0.7683 ± 0.0102	0.8176 ± 0.0087	Robust Optimization as Data Augmentation for Large-scale Graphs	-
PIN	0.7944 ± 1.40	-	Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes	-
GCN+GraphNorm	0.7883 ± 0.0100	0.7904 ± 0.0115	GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
DeeperGCN	0.7858 ± 0.0117	0.8427 ± 0.0063	DeeperGCN: All You Need to Train Deeper GCNs
GIN+virtual node	0.7707 ± 0.0149	0.8479 ± 0.0068	How Powerful are Graph Neural Networks?
CIN	0.8094 ± 0.0057	0.8277 ± 0.0099	Weisfeiler and Lehman Go Cellular: CW Networks
MorganFP+Rand. Forest	0.8060 ± 0.0010	0.8420 ± 0.0030	-	-
PNA	0.7905 ± 0.0132	0.8519 ± 0.0099	Principal Neighbourhood Aggregation for Graph Nets
DeeperGCN+FLAG	0.7942 ± 0.0120	0.8425 ± 0.0061	Robust Optimization as Data Augmentation for Large-scale Graphs	-
Nested GIN+virtual node	0.7834 ± 0.0186	0.8317 ± 0.0199	Nested Graph Neural Networks
CIN-small	0.8055 ± 0.0104	0.8310 ± 0.0102	Weisfeiler and Lehman Go Cellular: CW Networks
DGN	0.7970 ± 0.0097	0.8470 ± 0.0047	Directional Graph Networks
Graphormer	0.8051 ± 0.0053	0.8310 ± 0.0089	Do Transformers Really Perform Bad for Graph Representation?
HIMP	0.7880 ± 0.0082	Please tell us	Hierarchical Inter-Message Passing for Learning on Molecular Graphs

0 of 43 row(s) selected.