Show simple item record

dc.contributor.authorSuárez-Varela Maciá, José Rafael
dc.contributor.authorCarol Bosch, Sergi
dc.contributor.authorRusek, Krzysztof
dc.contributor.authorAlmasan Puscas, Felician Paul
dc.contributor.authorArias Vicente, Marta
dc.contributor.authorBarlet Ros, Pere
dc.contributor.authorCabellos Aparicio, Alberto
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.identifier.citationSuárez-varela, J. [et al.]. Challenging the generalization capabilities of Graph Neural Networks for network modeling. A: ACM Conference on Special Interest Group on Data Communication. "SIGCOMM’19: proceedings of the 2019 ACM SIGCOMM Conference posters and demos: August 19-23, 2019, Beijing, China". New York: Association for Computing Machinery (ACM), 2019, p. 114-115.
dc.description.abstractToday, network operators still lack functional network models able to make accurate predictions of end-to-end Key Performance Indicators (e.g., delay or jitter) at limited cost. Recently a novel Graph Neural Network (GNN) model called RouteNet was proposed as a cost-effective alternative to estimate the per-source/destination pair mean delay and jitter in networks. Thanks to its GNN architecture that operates over graph-structured data, RouteNet revealed an unprecedented ability to learn and model the complex relationships among topology, routing and input traffic in networks. As a result, it was able to make performance predictions with similar accuracy than resource-hungry packet-level simulators even in network scenarios unseen during training. In this demo, we will challenge the generalization capabilities of RouteNet with more complex scenarios, including larger topologies.
dc.description.sponsorshipThis work was supported by the Spanish MINECO under contract TEC2017-90034-C2-1-R (ALLIANCE), the Catalan Institution for Research and Advanced Studies (ICREA) and the AGH University of Science and Technology grant, under contract no. The research was also supported in part by PL-Grid Infrastructure.
dc.format.extent2 p.
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors
dc.subject.lcshMachine learning
dc.subject.lcshTelecommunication -- Traffic
dc.subject.otherGraph Neural Networks
dc.subject.otherNetwork modeling
dc.titleChallenging the generalization capabilities of Graph Neural Networks for network modeling
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacTelecomunicació -- Tràfic
dc.contributor.groupUniversitat Politècnica de Catalunya. CBA - Sistemes de Comunicacions i Arquitectures de Banda Ampla
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
dc.description.versionPostprint (author's final draft)
local.citation.authorSuárez-varela, J.; Carol, S.; Rusek, K.; Almasan, F.; Arias, M.; Barlet, P.; Cabellos-Aparicio, A.
local.citation.contributorACM Conference on Special Interest Group on Data Communication
local.citation.pubplaceNew York
local.citation.publicationNameSIGCOMM’19: proceedings of the 2019 ACM SIGCOMM Conference posters and demos: August 19-23, 2019, Beijing, China

Files in this item


This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder