Generalization bounds for graph convolutional neural networks via Rademacher complexity

This paper aims at studying the sample complexity of graph convolutional neural networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidden layer.

Data and Resources

Cite this as

Shaogao Lv (2024). Dataset: Generalization bounds for graph convolutional neural networks via Rademacher complexity. https://doi.org/10.57702/prahg1q0

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2102.10234
Author Shaogao Lv