Search Results

NeurIPS 2021 || DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks Paper

NeurIPS 2021 || DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks Paper

Graph Neural Networks

Graph Neural Networks

[Deep Graph Learning] 4.5 Generalized GNN layer and Dropout

[Deep Graph Learning] 4.5 Generalized GNN layer and Dropout

[Deep Graph Learning] 4.4 GNN batch normalization layer

[Deep Graph Learning] 4.4 GNN batch normalization layer

ICPRS2021 Paper 31

ICPRS2021 Paper 31

Robustness of Graph Neural Networks

Robustness of Graph Neural Networks

[Deep Graph Learning] 4.1 Point, batch and mini-batch gradient descent

[Deep Graph Learning] 4.1 Point, batch and mini-batch gradient descent

Martin Grohe: The Descriptive Complexity of Graph Neural Networks

Martin Grohe: The Descriptive Complexity of Graph Neural Networks

Improving Graph Neural Networks with Structural Adaptive Receptive Fields

Improving Graph Neural Networks with Structural Adaptive Receptive Fields

Employing knowledge graphs and Graph Neural Networks (GNNs) for patent research (AI & Patents 2021)

Employing knowledge graphs and Graph Neural Networks (GNNs) for patent research (AI & Patents 2021)

GNN-Surrogate: PacificVis2022 presentation

GNN-Surrogate: PacificVis2022 presentation

[Deep Graph Learning] 4.6 GNN inductive vs transductive learning

[Deep Graph Learning] 4.6 GNN inductive vs transductive learning