Transferability of Graph Neural Networks using Graphon and Sampling Theories
Not on the map. Why?
Abstract (arXiv)
Graph neural networks (GNNs) have become powerful tools for processing graph-based information in various domains. A desirable property of GNNs is transferability, where a trained network can swap in information from a different graph without retraining and retain its accuracy. A recent method of capturing transferability of GNNs is through the use of graphons, which are symmetric, measurable functions representing the limit of large dense graphs. In this work, we contribute to the application of graphons to GNNs by presenting an explicit two-layer graphon neural network (WNN) architecture. We prove its ability to approximate bandlimited graphon signals within a specified error tolerance using a minimal number of network weights. We then leverage this result, to establish the transferability of an explicit two-layer GNN over all sufficiently large graphs in a convergent sequence. Our work addresses transferability between both deterministic weighted graphs and simple random graphs and overcomes issues related to the curse of dimensionality that arise in other GNN results. The proposed WNN and GNN architectures offer practical solutions for handling graph data of varying sizes while maintaining performance guarantees without extensive retraining.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 63 references that are in the map. First posted on arXiv 25 Jul 2023.
Builds on
27 of 63 references.
References · 27
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
- 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
- 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 117
- 2019Transferability of Spectral Graph Convolutional Neural Networkscited by 90
- 2020Convergence and Stability of Graph Convolutional Networks on Large Random Graphscited by 75
- 2021Transferability of Graph Neural Networks: an Extended Graphon Approachcited by 51
- 2018Content-Based Citation Recommendationcited by 43
- 2021Transferability Properties of Graph Neural Networkscited by 42
- 2013Stochastic blockmodel approximation of a graphon: Theory and consistent estimationcited by 38
15 more
- 2018Exponential Convergence of the Deep Neural Network Approximation for Analytic Functionscited by 38
- 2020Graphon Signal Processingcited by 37
- 2017The game theoretic p-Laplacian and semi-supervised learning with few labelscited by 22
- 2021Learning by Transference: Training Graph Neural Networks on Growing Graphscited by 22
- 2020Graphon Filters: Graph Signal Processing in the Limitcited by 16
- 2020Graph and graphon neural network stabilitycited by 15
- 2022Learning Sparse Graphon Mean Field Gamescited by 14
- 2019Band-limited Training and Inference for Convolutional Neural Networkscited by 13
- 2022Convolutional Neural Networks on Manifolds: From Graphs and Backcited by 13
- 2020Graphon Pooling in Graph Neural Networkscited by 11
- 2021Structured Citation Trend Prediction Using Graph Neural Networkscited by 11
- 2019Subsampling Sparse Graphons Under Minimal Assumptionscited by 5
- 2021Training Graph Neural Networks by Graphon Estimationcited by 4
- 2022Theoretical guarantees for the advantage of GNNs over NNs in generalizing bandlimited functions on Euclidean cubescited by 4
- 2022Stochastic Block Smooth Graphon Modelcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.