mlsanityData to 7 Oct 2026

Training Graph Neural Networks on Growing Stochastic Graphs

arXiv 2210.15567 ↗First posted 27 Oct 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To overcome these limitations, proposed methods rely on training GNNs in smaller number of nodes, and then transferring the GNN to larger graphs. Even though these methods are able to bound the difference between the output of the GNN with different number of nodes, they do not provide guarantees against the optimal GNN on the very large graph. In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon. We propose to grow the size of the graph as we train, and we show that our proposed methodology -- learning by transference -- converges to a neighborhood of a first order stationary point on the graphon data. A numerical experiment validates our proposed approach.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

18 of 29 references.

References · 18

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  7. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  10. 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
  11. 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 117
  12. 2018Convolutional Neural Network Architectures for Signals Supported on Graphscited by 94
6 more
  1. 2019Optimal Wireless Resource Allocation with Random Edge Graph Neural Networkscited by 90
  2. 2021Transferability Properties of Graph Neural Networkscited by 42
  3. 2020Learning to Hash with Graph Neural Networks for Recommender Systemscited by 31
  4. 2021Learning by Transference: Training Graph Neural Networks on Growing Graphscited by 22
  5. 2019Invariance-Preserving Localized Activation Functions for Graph Neural Networkscited by 14
  6. 2019The Graphon Fourier Transformcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2.

5 papers.

  1. 2023Graph Neural Tangent Kernel: Convergence on Large Graphscited by 16
  2. 2024Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functionscited by 6
  3. 2023Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimizationcited by 4
  4. 2023Limited Communications Distributed Optimization via Deep Unfolded Distributed ADMMcited by 2
  5. 2024Distributed Training of Large Graph Neural Networks with Variable Communication Ratescited by 0