Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization

Abstract

Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability from a theoretical perspective. Existing theoretical research has primarily focused on the analysis of single-layer GCNs, while a comprehensive theoretical exploration of the stability and generalization of deep GCNs remains limited. In this paper, we bridge this gap by delving into the stability and generalization properties of deep GCNs, aiming to provide valuable insights by characterizing rigorously the associated upper bounds. Our theoretical results reveal that the stability and generalization of deep GCNs are influenced by certain key factors, such as the maximum absolute eigenvalue of the graph filter operators and the depth of the network. Our theoretical studies contribute to a deeper understanding of the stability and generalization properties of deep GCNs, potentially paving the way for developing more reliable and well-performing models.

50 pages, 3 figures, published in IEEE Trans. Pattern Anal. Mach. Intell. 2025

References in corpus (6)

• A Comprehensive Survey on Graph Neural Networks
• Graph Neural Networks with convolutional ARMA filters
• A Gentle Introduction to Deep Learning for Graphs
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks