Deeper Insights Into Deep Graph Convolutional Networks: Stability and Generalization
Top Cited Papers
- 6 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1707-1719
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.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- A tighter generalization error bound for wide GCN based on loss landscapeApplied and Computational Harmonic Analysis, 2025
- Homophily modulates double descent generalization in graph convolution networksProceedings of the National Academy of Sciences, 2024
- Emotional conversation generation with heterogeneous graph neural networkArtificial Intelligence, 2022
- Multi-view graph convolutional networks with attention mechanismArtificial Intelligence, 2022
- Graph Neural Networks: Foundations, Frontiers, and Applications2022
- Deep Learning on Graphs2021
- A gentle introduction to deep learning for graphsNeural Networks, 2020
- Graph Representation Learning2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- The Vapnik–Chervonenkis dimension of graph and recursive neural networksNeural Networks, 2018