MLLGFeb 20, 2021

Generalization bounds for graph convolutional neural networks via Rademacher complexity

arXiv:2102.10234v123 citations
Originality Incremental advance
AI Analysis

This work provides theoretical insights for researchers in graph machine learning, though it is incremental as it builds on existing complexity analysis methods.

The paper tackles the problem of understanding the sample complexity of graph convolutional networks (GCNs) by deriving tight upper and lower bounds for Rademacher complexity, showing explicit dependencies on graph properties like the largest eigenvalue of filters and degree distribution.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes