Generalization bounds for graph convolutional neural networks via Rademacher complexity
arXiv:2102.10234
Abstract
This paper aims at studying the sample complexity of graph convolutional networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidden layer. Under regularity conditions, theses derived complexity bounds explicitly depend on the largest eigenvalue of graph convolution filter and the degree distribution of the graph. Again, we provide a lower bound of Rademacher complexity for GCNs to show optimality of our derived upper bounds. Taking two commonly used examples as representatives, we discuss the implications of our results in designing graph convolution filters an graph distribution.
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Geometric deep learning: going beyond Euclidean data
- Graph Neural Networks: A Review of Methods and Applications
- Interaction Networks for Learning about Objects, Relations and Physics
- Gated Graph Sequence Neural Networks
- Spectrally-normalized margin bounds for neural networks
- Unifying local and non-local signal processing with graph CNNs
- A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
- Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case