GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
Lists
Only you see this
Abstract
We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size without dropping any data. While existing solutions weaken the expressive power of message passing due to sub-sampling of edges or non-trainable propagations, our approach is provably able to maintain the expressive power of the original GNN. We achieve this by providing approximation error bounds of historical embeddings and show how to tighten them in practice. Empirically, we show that the practical realization of our framework, PyGAS, an easy-to-use extension for PyTorch Geometric, is both fast and memory-efficient, learns expressive node representations, closely resembles the performance of their non-scaling counterparts, and reaches state-of-the-art performance on large-scale graphs.
BibTeX
@inproceedings{fey2021gnnautoscale,
author = {Matthias Fey and Jan E. Lenssen and Frank Weichert and Jure Leskovec},
title = {{GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings}},
booktitle = {International Conference on Machine Learning},
year = {2021},
}| Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks | arXiv · 2024 |
| Deep Graph Representation Learning | Mach. Learn. Under Resour. Constraints Vol. 1 · 2022 |
| FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training | arXiv · 2023 |
| LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation | ICML · 2023 |
| LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges | arXiv · 2025 |
| WaveGAS: Waveform Relaxation for Scaling Graph Neural Networks | arXiv · 2025 |