Graph Regression On Zinc

MAE

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
Graph-JEPA	0.434	Graph-level Representation Learning with Joint-Embedding Predictive Architectures
FactorGCN	0.366	Factorizable Graph Convolutional Networks
ChebNet	0.360	An Experimental Study of the Transferability of Spectral Graph Networks
BoP	0.297	From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis
MMA	0.156	Multi-Mask Aggregators for Graph Neural Networks
PNA	0.142	Principal Neighbourhood Aggregation for Graph Nets
CRaWl	0.101	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
PIN	0.096	Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
CIN-small	0.094	Weisfeiler and Lehman Go Cellular: CW Networks
CIN++-small	0.091	CIN++: Enhancing Topological Message Passing
CRaWl+VN	0.088	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
CIN	0.079	Weisfeiler and Lehman Go Cellular: CW Networks
EIGENFORMER	0.077	Graph Transformers without Positional Encodings
CIN++-500k	0.077	CIN++: Enhancing Topological Message Passing
GraphMLPMixer	0.075 ± 0.001	A Generalization of ViT/MLP-Mixer to Graphs
CIN++	0.074	CIN++: Enhancing Topological Message Passing
SAGNN	0.072±0.002	Substructure Aware Graph Neural Networks
GPS	0.070 ± 0.002	Recipe for a General, Powerful, Scalable Graph Transformer
GINE	0.070 ± 0.004	Recipe for a General, Powerful, Scalable Graph Transformer
PDF	0.066 ± 0.002	Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

0 of 27 row(s) selected.