Graph Neural Networks (GNNs) are a form of deep learning that enable a wide range of machine learning applications on graph-structured data. The learning of GNNs, however, is known to pose challenges for memory-constrained devices such as GPUs. In this paper, we study exact compression as a way to reduce the memory requirements of learning GNNs on large graphs. In particular, we adopt a formal approach to compression and propose a methodology that transforms GNN learning problems into provably equivalent compressed GNN learning problems. In a preliminary experimental evaluation, we give insights into the compression ratios that can be obtained on real-world graphs and apply our methodology to an existing GNN benchmark.
@article{arxiv.2304.14793,
title = {Learning Graph Neural Networks using Exact Compression},
author = {Jeroen Bollen and Jasper Steegmans and Jan Van den Bussche and Stijn Vansummeren},
journal= {arXiv preprint arXiv:2304.14793},
year = {2023}
}
Comments
Extended version of the paper to be published in the proceedings of the 6th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA), held in conjunction with SIGMOD/PODS 2023