Graph Regression On Zinc 500K

Metriken

MAE

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	MAE	Paper Title
CSA	0.056	Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers
CRaWl	0.101	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
GatedGCN-LSPE	0.090	Graph Neural Networks with Learnable Structural and Positional Representations
GatedGCN-PE	0.214	Benchmarking Graph Neural Networks
GIN	0.526	How Powerful are Graph Neural Networks?
CIN-small	0.094	Weisfeiler and Lehman Go Cellular: CW Networks
GPS	0.070	Recipe for a General, Powerful, Scalable Graph Transformer
GPTrans-Nano	0.077	Graph Propagation Transformer for Graph Representation Learning
PNA-SignNet	0.084	Sign and Basis Invariant Networks for Spectral Graph Representation Learning
3WLGNN	0.303	Provably Powerful Graph Networks
PDF	0.066	Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
GraphGPS + HDSE	0.062	Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
SAGNN	0.072	Substructure Aware Graph Neural Networks
B-PEARL	0.0655	Learning Efficient Positional Encodings with Graph Neural Networks
MoNet	0.292	Geometric deep learning on graphs and manifolds using mixture model CNNs
CRaWl+VN	0.088	Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
R-PEARL	0.0696	Learning Efficient Positional Encodings with Graph Neural Networks
PNA-LSPE	0.095	Graph Neural Networks with Learnable Structural and Positional Representations
EGT	0.108	Global Self-Attention as a Replacement for Graph Convolution
MPNN (sum)	0.145	Neural Message Passing for Quantum Chemistry

0 of 36 row(s) selected.