# Scaling R-GCN Training with Graph Summarization

arXiv: https://arxiv.org/abs/2203.02622 · HTML: https://mlsanity.com/paper/2203.02622/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 5 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks](https://mlsanity.com/paper/2104.06700/) (2021)
- [GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding](https://mlsanity.com/paper/1910.02370/) (2019)
- [Graph Summarization Methods and Applications: A Survey](https://mlsanity.com/paper/1612.04883/) (2016)
- [A Degeneracy Framework for Scalable Graph Autoencoders](https://mlsanity.com/paper/1902.08813/) (2019)
- [Relational Graph Convolutional Networks: A Closer Look](https://mlsanity.com/paper/2107.10015/) (2021)

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation](https://mlsanity.com/paper/2402.03358/) (2024)
- [A Comprehensive Survey on Graph Summarization with Graph Neural Networks](https://mlsanity.com/paper/2302.06114/) (2023)
- [Learning Graph Neural Networks using Exact Compression](https://mlsanity.com/paper/2304.14793/) (2023)
- [A Split-Window Transformer for Multi-Model Sequence Spammer Detection using Multi-Model Variational Autoencoder](https://mlsanity.com/paper/2502.16483/) (2025)
- [Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark](https://mlsanity.com/paper/2606.12581/) (2026)

## Abstract (arXiv)

Training of Relational Graph Convolutional Networks (R-GCN) is a memory intense task. The amount of gradient information that needs to be stored during training for real-world graphs is often too large for the amount of memory available on most GPUs. In this work, we experiment with the use of graph summarization techniques to compress the graph and hence reduce the amount of memory needed. After training the R-GCN on the graph summary, we transfer the weights back to the original graph and attempt to perform inference on it. We obtain reasonable results on the AIFB, MUTAG and AM datasets. Our experiments show that training on the graph summary can yield a comparable or higher accuracy to training on the original graphs.Furthermore, if we take the time to compute the summary out of the equation, we observe that the smaller graph representations obtained with graph summarization methods reduces the computational overhead. However, further experiments are needed to evaluate additional graph summary models and whether our findings also holds true for very large graphs.