Graph Regression On Zinc 500K

Metrics

MAE

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	MAE
self-attention-in-colors-another-take-on	0.056
graph-learning-with-1d-convolutions-on-random	0.101
graph-neural-networks-with-learnable-1	0.090
benchmarking-graph-neural-networks	0.214
how-powerful-are-graph-neural-networks	0.526
weisfeiler-and-lehman-go-cellular-cw-networks	0.094
recipe-for-a-general-powerful-scalable-graph	0.070
graph-propagation-transformer-for-graph	0.077
sign-and-basis-invariant-networks-for	0.084
provably-powerful-graph-networks	0.303
towards-better-graph-representation-learning	0.066
transformers-for-capturing-multi-level-graph	0.062
substructure-aware-graph-neural-networks	0.072
learning-efficient-positional-encodings-with	0.0655
geometric-deep-learning-on-graphs-and	0.292
graph-learning-with-1d-convolutions-on-random	0.088
learning-efficient-positional-encodings-with	0.0696
graph-neural-networks-with-learnable-1	0.095
edge-augmented-graph-transformers-global-self	0.108
neural-message-passing-for-quantum-chemistry	0.145
unlocking-the-potential-of-classic-gnns-for	0.065
on-the-equivalence-between-graph-isomorphism	0.353
graph-neural-networks-with-learnable-1	0.104
improving-spectral-graph-convolution-for	0.0698
equivariant-matrix-function-neural-networks	0.063
extending-the-design-space-of-graph-neural-1	0.059
masked-attention-is-all-you-need-for-graphs	0.051
graph-inductive-biases-in-transformers	0.059
residual-gated-graph-convnets	0.282
improving-graph-neural-network-expressivity	0.101
benchmarking-graph-neural-networks	0.214
do-transformers-really-perform-bad-for-graph	0.122
neural-message-passing-for-quantum-chemistry	0.252
ckgconv-general-graph-convolution-with	5.9
inductive-representation-learning-on-large	0.398
weisfeiler-and-lehman-go-cellular-cw-networks	0.079