Graph Regression On Zinc

Métriques

MAE

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	MAE	Paper Title	Repository
GPS	0.070 ± 0.002	Recipe for a General, Powerful, Scalable Graph Transformer
N2-GNN	0.059	Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
PIN	0.096	Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes	-
PDF	0.066 ± 0.002	Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
ESA + rings + NodeRWSE + EdgeRWSE	0.051	An end-to-end attention-based approach for learning on graphs	-
CSA	0.056	Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers
CRaWl+VN	0.088	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
GraphMLPMixer	0.075 ± 0.001	A Generalization of ViT/MLP-Mixer to Graphs
BoP	0.297	From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis
MMA	0.156	Multi-Mask Aggregators for Graph Neural Networks
GRIT	0.059	Graph Inductive Biases in Transformers without Message Passing
ChebNet	0.360	An Experimental Study of the Transferability of Spectral Graph Networks
NeuralWalker	0.065 ± 0.001	Learning Long Range Dependencies on Graphs via Random Walks
FactorGCN	0.366	Factorizable Graph Convolutional Networks
SAGNN	0.072±0.002	Substructure Aware Graph Neural Networks
CIN-small	0.094	Weisfeiler and Lehman Go Cellular: CW Networks
PNA	0.142	Principal Neighbourhood Aggregation for Graph Nets
EIGENFORMER	0.077	Graph Transformers without Positional Encodings	-
CIN++	0.074	CIN++: Enhancing Topological Message Passing
TIGT	0.057	Topology-Informed Graph Transformer

0 of 27 row(s) selected.