Graph Classification On Nci109

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	Accuracy
self-attention-graph-pooling	67.86
gaussian-induced-convolution-for-graphs	82.86
spectral-multigraph-networks-for-discovering	82.0
principal-neighbourhood-aggregation-for-graph	83.382±1.045
learning-metrics-for-persistence-based-2	87.3
recipe-for-a-general-powerful-scalable-graph	81.256±0.501
graph2vec-learning-distributed	74.26
cell-attention-networks	83.6
graph-attention-networks	82.560±0.601
dropgnn-random-dropouts-increase-the	83.961±1.141
how-attentive-are-graph-attention-networks	83.092±0.764
hierarchical-graph-pooling-with-structure	80.67
pre-training-graph-neural-networks-on	77.54±1.51
graph-isomorphism-unet	77
generalizing-topological-graph-neural	84.0
subgraph-networks-with-application-to	71.06
transitivity-preserving-graph-representation	75.45±1.26
propagation-kernels-efficient-graph-kernels	83.5
semi-supervised-classification-with-graph	83.140±1.248
asap-adaptive-structure-aware-pooling-for	70.07
unsupervised-inductive-whole-graph-embedding	69.17
cin-enhancing-topological-message-passing	84.5
masked-attention-is-all-you-need-for-graphs	84.976±0.551
self-attention-graph-pooling	74.06
graph-convolutional-networks-with	74.90
provably-powerful-graph-networks	82.23
pure-transformers-are-powerful-graph-learners	72.077±1.883
on-valid-optimal-assignment-kernels-and	86.3
relational-reasoning-over-spatial-temporal	75.85
when-work-matters-transforming-classical	80.66
capsule-neural-networks-for-graph	58.04
do-transformers-really-perform-bad-for-graph	74.879±1.183
improving-spectral-graph-convolution-for	83.62
how-powerful-are-graph-neural-networks	84.155±0.812
unsupervised-inductive-whole-graph-embedding	74.48
towards-a-practical-k-dimensional-weisfeiler	84.7
dynamic-edge-conditioned-filters-in	82.14