Graph Regression On Zinc 500K

MAE

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
CKGCN	5.9	CKGConv: General Graph Convolution with Continuous Kernels
GIN	0.526	How Powerful are Graph Neural Networks?
GraphSage	0.398	Inductive Representation Learning on Large Graphs
RingGNN	0.353	On the equivalence between graph isomorphism testing and function approximation with GNNs
3WLGNN	0.303	Provably Powerful Graph Networks
MoNet	0.292	Geometric deep learning on graphs and manifolds using mixture model CNNs
GatedGCN	0.282	Residual Gated Graph ConvNets
MPNN (max)	0.252	Neural Message Passing for Quantum Chemistry
GatedGCN-PE	0.214	Benchmarking Graph Neural Networks
GatedGCN-E-PE	0.214	Benchmarking Graph Neural Networks
MPNN (sum)	0.145	Neural Message Passing for Quantum Chemistry
Graphormer-SLIM	0.122	Do Transformers Really Perform Bad for Graph Representation?
EGT	0.108	Global Self-Attention as a Replacement for Graph Convolution
SAN-LSPE	0.104	Graph Neural Networks with Learnable Structural and Positional Representations
CRaWl	0.101	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
GSN	0.101	Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
PNA-LSPE	0.095	Graph Neural Networks with Learnable Structural and Positional Representations
CIN-small	0.094	Weisfeiler and Lehman Go Cellular: CW Networks
GatedGCN-LSPE	0.090	Graph Neural Networks with Learnable Structural and Positional Representations
CRaWl+VN	0.088	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing

0 of 36 row(s) selected.