GIN is provably as expressive as the Weisfeiler-Lehman graph isomorphism test, while GCN and GraphSAGE have strictly weaker discriminative power on some graphs.
Dropout: a simple way to prevent neural networks from overfitting
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
DropAttention regularizes attention weights in fully-connected self-attention networks to reduce overfitting and improve performance.
Shapley value and variational importance switch methods produce consistent rankings of filter importance in CNNs, enabling compression and interpretability.
citing papers explorer
-
How Powerful are Graph Neural Networks?
GIN is provably as expressive as the Weisfeiler-Lehman graph isomorphism test, while GCN and GraphSAGE have strictly weaker discriminative power on some graphs.
-
DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks
DropAttention regularizes attention weights in fully-connected self-attention networks to reduce overfitting and improve performance.
-
Neuron ranking -- an informed way to condense convolutional neural networks architecture
Shapley value and variational importance switch methods produce consistent rankings of filter importance in CNNs, enabling compression and interpretability.