The authors prove PAC-Bayesian generalization bounds for one- and two-layer graph convolutional networks in inductive node classification, where new nodes arrive after training.
User-friendly introduction to PAC-Bayes bounds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification
The authors prove PAC-Bayesian generalization bounds for one- and two-layer graph convolutional networks in inductive node classification, where new nodes arrive after training.