A new PAC-Bayesian framework for GCNs derives a family of generalization bounds that embed graph topology via structured sensitivity matrices from spatial and spectral perspectives, recovering prior bounds as special cases while claiming tighter results.
Generalization, expressivity, and universality of graph neural networks on attributed graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks
A new PAC-Bayesian framework for GCNs derives a family of generalization bounds that embed graph topology via structured sensitivity matrices from spatial and spectral perspectives, recovering prior bounds as special cases while claiming tighter results.