On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the continuous-depth architecture of Neural ODEs, offering a scalable and principled framework for modeling dynamics on graphs. In this paper, we present a rigorous convergence analysis of GNDEs with time-varying parameters in the infinite-node limit, providing theoretical insights into their size transferability. To this end, we introduce Graphon Neural Differential Equations (Graphon-NDEs) as the infinite-node limit of GNDEs and establish their well-posedness. Leveraging tools from graphon theory and dynamical systems, we prove the trajectory-wise convergence of GNDE solutions to Graphon-NDE solutions. Moreover, we derive explicit convergence rates under two deterministic graph sampling regimes: (1) weighted graphs sampled from smooth graphons, and (2) unweighted graphs sampled from 0,1-valued (discontinuous) graphons. We further establish size transferability bounds, providing theoretical justification for the practical strategy of transferring GNDE models trained on moderate-sized graphs to larger, structurally similar graphs without retraining. Numerical experiments using synthetic and real data support our theoretical findings.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 49 of its 91 references that are in the map. First posted on arXiv 4 Oct 2025.
Builds on
49 of 91 references.
References · 49
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
- 2019Multi-scale Attributed Node Embeddingcited by 548
- 2019Graph Transformer Networkscited by 523
- 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
37 more
- 2021GRAND: Graph Neural Diffusioncited by 258
- 2019Graph Neural Ordinary Differential Equationscited by 154
- 2020Dissecting Neural ODEscited by 153
- 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
- 2019Stability Properties of Graph Neural Networkscited by 127
- 2022Graph-Coupled Oscillator Networkscited by 124
- 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 118
- 2019Continuous Graph Neural Networkscited by 114
- 2019Transferability of Spectral Graph Convolutional Neural Networkscited by 92
- 2020Convergence and Stability of Graph Convolutional Networks on Large Random Graphscited by 76
- 2022Theory of Graph Neural Networks: Representation and Learningcited by 61
- 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
- 2021Transferability of Graph Neural Networks: an Extended Graphon Approachcited by 53
- 2021Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networkscited by 39
- 2020Graphon Signal Processingcited by 37
- 2021Interpretable Stability Bounds for Spectral Graph Filterscited by 28
- 2022Do Residual Neural Networks discretize Neural Ordinary Differential Equations?cited by 27
- 2021On the Universality of Graph Neural Networks on Large Random Graphscited by 26
- 2020On the Stability of Graph Convolutional Neural Networks under Edge Rewiringcited by 25
- 2023Generalizing Graph ODE for Learning Complex System Dynamics across Environmentscited by 23
- 2022Implicit Graphon Neural Representationcited by 19
- 2023Limits, approximation and size transferability for GNNs on sparse graphs via graphopscited by 18
- 2020Graphon Filters: Graph Signal Processing in the Limitcited by 16
- 2023Graph Neural Tangent Kernel: Convergence on Large Graphscited by 16
- 2023A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networkscited by 16
- 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
- 2023What functions can Graph Neural Networks compute on random graphs? The role of Positional Encodingcited by 12
- 2019Neural ODEs as the Deep Limit of ResNets with constant weightscited by 10
- 2021Robust Graph Neural Networks via Probabilistic Lipschitz Constraintscited by 10
- 2013The nonlinear heat equation on dense graphs and graph limitscited by 9
- 2022Convergence of Invariant Graph Networkscited by 9
- 2023Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphscited by 9
- 2024Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systemscited by 8
- 2025Higher-Order Graphon Neural Networks: Approximation and Cut Distancecited by 7
- 2023Graph Neural Ordinary Differential Equations-based method for Collaborative Filteringcited by 5
- 2022Learning Physics-Consistent Particle Interactionscited by 4
- 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learningcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.