Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40622
Title: | Learning Graph Neural Networks using Exact Compression | Authors: | BOLLEN, Jeroen STEEGMANS, Jasper VAN DEN BUSSCHE, Jan VANSUMMEREN, Stijn |
Editors: | Hartig, O. Yoshida, Y. |
Issue Date: | 2023 | Publisher: | ASSOC COMPUTING MACHINERY | Source: | Abstract: | 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. | Notes: | Bollen, J (corresponding author), UHasselt, Data Sci Inst, Hasselt, Belgium. jeroen.bollen@uhasselt.be; jasper.steegmans@uhasselt.be; jan.vandenbussche@uhasselt.be; stijn.vansummeren@uhasselt.be |
Keywords: | CCS Concepts;Information systems → Graph-based database models;;Computing methodologies → Neural networks Keywords Graph neural networks, color refinement, compression | Document URI: | http://hdl.handle.net/1942/40622 | ISBN: | 9798400702013 | DOI: | 10.1145/3594778.3594878 | ISI #: | 001109707400008 | Rights: | 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. | Category: | C1 | Type: | Proceedings Paper |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
GRADES-NDA_2023_paper_3843.pdf | Peer-reviewed author version | 503.59 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.