Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40622
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | BOLLEN, Jeroen | - |
dc.contributor.author | STEEGMANS, Jasper | - |
dc.contributor.author | VAN DEN BUSSCHE, Jan | - |
dc.contributor.author | VANSUMMEREN, Stijn | - |
dc.contributor.editor | Hartig, O. | - |
dc.contributor.editor | Yoshida, Y. | - |
dc.date.accessioned | 2023-07-20T12:54:45Z | - |
dc.date.available | 2023-07-20T12:54:45Z | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-07-18T09:48:33Z | - |
dc.identifier.citation | - | |
dc.identifier.isbn | 9798400702013 | - |
dc.identifier.uri | http://hdl.handle.net/1942/40622 | - |
dc.description.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. | - |
dc.description.sponsorship | We thank Floris Geerts for helpful discussions and the anonymous reviewers for their constructive comments. S. Vansummeren and J. Steegmans were supported by the Bijzonder Onderzoeksfonds (BOF) of Hasselt University under Grants No. BOF20ZAP02 and BOF21D11VDBJ. This work was further supported by the Research Foundation Flanders (FWO) under research project Grant No. G019222N. We acknowledge computing resources and services provided by the VSC (Flemish Supercomputer Center), funded by the Research Foundation – Flanders (FWO) and the Flemish Government. | - |
dc.language.iso | en | - |
dc.publisher | ASSOC COMPUTING MACHINERY | - |
dc.rights | 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. | - |
dc.subject.other | CCS Concepts | - |
dc.subject.other | Information systems → Graph-based database models; | - |
dc.subject.other | Computing methodologies → Neural networks Keywords Graph neural networks, color refinement, compression | - |
dc.title | Learning Graph Neural Networks using Exact Compression | - |
dc.type | Proceedings Paper | - |
local.bibliographicCitation.conferencename | 6th ACM SIGMOD Joint International Workshop on Graph Data Management Experiences and Systems / Workshop on Network Data Analytics (GRADES-NDA) | - |
local.bibliographicCitation.conferenceplace | Seattle, WA | - |
dc.identifier.epage | 9 | - |
dc.identifier.spage | 1 | - |
local.format.pages | 9 | - |
local.bibliographicCitation.jcat | C1 | - |
dc.description.notes | Bollen, J (corresponding author), UHasselt, Data Sci Inst, Hasselt, Belgium. | - |
dc.description.notes | jeroen.bollen@uhasselt.be; jasper.steegmans@uhasselt.be; | - |
dc.description.notes | jan.vandenbussche@uhasselt.be; stijn.vansummeren@uhasselt.be | - |
local.publisher.place | 1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES | - |
local.type.refereed | Refereed | - |
local.type.specified | Proceedings Paper | - |
dc.identifier.doi | 10.1145/3594778.3594878 | - |
dc.identifier.arxiv | https://arxiv.org/abs/2304.14793 | - |
dc.identifier.isi | 001109707400008 | - |
local.provider.type | - | |
local.description.affiliation | [Bollen, Jeroen; Steegmans, Jasper; Van den Bussche, Jan; Vansummeren, Stijn] UHasselt, Data Sci Inst, Hasselt, Belgium. | - |
local.uhasselt.international | no | - |
item.fulltext | With Fulltext | - |
item.fullcitation | BOLLEN, Jeroen; STEEGMANS, Jasper; VAN DEN BUSSCHE, Jan & VANSUMMEREN, Stijn (2023) Learning Graph Neural Networks using Exact Compression. | - |
item.accessRights | Open Access | - |
item.contributor | BOLLEN, Jeroen | - |
item.contributor | STEEGMANS, Jasper | - |
item.contributor | VAN DEN BUSSCHE, Jan | - |
item.contributor | VANSUMMEREN, Stijn | - |
item.contributor | Hartig, O. | - |
item.contributor | Yoshida, Y. | - |
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.