Graph Regression On Lipophilicity

RMSE@80%Train

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	RMSE@80%Train	Paper Title	Repository
Random Forests	1.16	CensNet: Convolution with Edge-Node Switching in Graph Neural Networks	-
CensNet	0.93	CensNet: Convolution with Edge-Node Switching in Graph Neural Networks	-
Weave	-	Molecular Graph Convolutions: Moving Beyond Fingerprints
GIN	-	How Powerful are Graph Neural Networks?
ESA (Edge set attention, no positional encodings)	-	An end-to-end attention-based approach for learning on graphs	-
XGBoost	-	Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
SGC	-	Simplifying Graph Convolutional Networks
ProtoS-L2	-	Optimal Transport Graph Neural Networks
RF	-	Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
GAT	-	Graph Attention Networks
AGNN	-	Attention-based Graph Neural Network for Semi-supervised Learning
DropGIN	-	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
ARMA	-	Graph Neural Networks with convolutional ARMA filters
GraphGPS	-	Recipe for a General, Powerful, Scalable Graph Transformer
C-SGEN+ Fingerprint	-	Molecule Property Prediction Based on Spatial Graph Embedding
PNA	-	Principal Neighbourhood Aggregation for Graph Nets
MPNN	-	Neural Message Passing for Quantum Chemistry
GCN	-	Semi-Supervised Classification with Graph Convolutional Networks
TokenGT	-	Pure Transformers are Powerful Graph Learners
GC	-	Convolutional Networks on Graphs for Learning Molecular Fingerprints

0 of 23 row(s) selected.