Graph Regression On Peptides Struct

Metriken

MAE

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Vergleichstabelle

Modellname	MAE
drew-dynamically-rewired-message-passing-with	0.2536±0.0015
diffusing-graph-attention	0.2461±0.0010
cin-enhancing-topological-message-passing	0.2523
where-did-the-gap-go-reassessing-the-long	0.2477±0.0009
from-primes-to-paths-enabling-fast-multi	0.25
exphormer-sparse-transformers-for-graphs	0.2481±0.0007
learning-probabilistic-symmetrization-for-1	0.2559
pure-transformers-are-powerful-graph-learners	0.2489±0.0013
molecular-fingerprints-are-strong-models-for	0.2459
neural-priority-queues-for-graph-neural	0.2589±0.0031
learning-long-range-dependencies-on-graphs	0.2463 ± 0.0005
molecular-fingerprints-are-strong-models-for	0.2432
where-did-the-gap-go-reassessing-the-long	0.2460±0.0007
long-range-graph-benchmark	0.2529±0.0016
long-range-graph-benchmark	0.2683±0.0043
graph-transformers-without-positional	0.2599
masked-attention-is-all-you-need-for-graphs	0.2393±0.0004
long-range-graph-benchmark	0.3496±0.0013
recipe-for-a-general-powerful-scalable-graph	0.2500±0.0005
a-generalization-of-vit-mlp-mixer-to-graphs	0.2475±0.0015
path-neural-networks-expressive-and-accurate	0.2545±0.0032
masked-attention-is-all-you-need-for-graphs	0.2453±0.0003
long-range-graph-benchmark	0.3547±0.0045
ckgconv-general-graph-convolution-with	0.2477
panda-expanded-width-aware-message-passing	0.3272±0.0001
where-did-the-gap-go-reassessing-the-long	0.2473±0.0017
where-did-the-gap-go-reassessing-the-long	0.2509±0.0014
long-range-graph-benchmark	0.3420±0.0013
a-generalization-of-vit-mlp-mixer-to-graphs	0.2449±0.0016
graph-inductive-biases-in-transformers	0.2460±0.0012
on-the-connection-between-mpnn-and-graph	0.2488±0.0021
next-level-message-passing-with-hierarchical	0.2421±0.0007
topology-informed-graph-transformer	0.2485
unlocking-the-potential-of-classic-gnns-for	0.2421 ± 0.0016
molecular-fingerprints-are-strong-models-for	0.2438
multiresolution-graph-transformers-and	0.2453±0.0025
simple-and-deep-graph-convolutional-networks-1	0.3471±0.0010
long-range-graph-benchmark	0.3357±0.0006
long-range-graph-benchmark	0.2545±0.0012