Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Learning on streaming graphs with experience replay
University of Edinburgh, UK.
ETH Zurich, Switzerland.
RISE Research Institutes of Sweden, Digitala system, Datavetenskap. KTH Royal Institute of Technology, Sweden.ORCID-id: 0000-0002-9351-8508
Boston University, USA.
2022 (engelsk)Inngår i: Proceedings of the ACM Symposium on Applied Computing, Association for Computing Machinery , 2022, s. 470-478Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Graph Neural Networks (GNNs) have recently achieved good performance in many predictive tasks involving graph-structured data. However, the majority of existing models consider static graphs only and do not support training on graph streams. While inductive representation learning can generate predictions for unseen vertices, these are only accurate if the learned graph structure and properties remain stable over time. In this paper, we study the problem of employing experience replay to enable continuous graph representation learning in the streaming setting. We propose two online training methods, Random-Based Rehearsal-RBR, and Priority-Based Rehearsal-PBR, which avoid retraining from scratch when changes occur. Our algorithms are the first streaming GNN models capable of scaling to million-edge graphs with low training latency and without compromising accuracy. We evaluate the accuracy and training performance of these experience replay methods on the node classification problem using real-world streaming graphs of various sizes and domains. Our results demonstrate that PBR and RBR achieve orders of magnitude faster training as compared to offline methods while providing high accuracy and resiliency to concept drift.

sted, utgiver, år, opplag, sider
Association for Computing Machinery , 2022. s. 470-478
Emneord [en]
graph convolutional networks, online learning, streaming graphs, Convolutional neural networks, E-learning, Graph algorithms, Graph neural networks, World Wide Web, Convolutional networks, Experience replay, Graph convolutional network, Graph properties, Graph structured data, Graph structures, Performance, Streaming graph, Graphic methods
HSV kategori
Identifikatorer
URN: urn:nbn:se:ri:diva-59332DOI: 10.1145/3477314.3507113Scopus ID: 2-s2.0-85130388203ISBN: 9781450387132 (digital)OAI: oai:DiVA.org:ri-59332DiVA, id: diva2:1673103
Konferanse
37th ACM/SIGAPP Symposium on Applied Computing, SAC 2022, 25 April 2022 through 29 April 2022
Merknad

 Funding details: Stiftelsen för Strategisk Forskning, SSF, BD15-0006; Funding text 1: The authors are pleased to acknowledge that the computational work reported on in this paper was performed on the Shared Computing Cluster which is administered by Boston University’s Research Computing Services [1]. Furthermore, this work has been partially funded by the Continuous Deep Analytics project granted by the Swedish Foundation for Strategic Research (SSF) under Grant No.: BD15-0006.

Tilgjengelig fra: 2022-06-20 Laget: 2022-06-20 Sist oppdatert: 2023-06-02bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Carbone, Paris

Søk i DiVA

Av forfatter/redaktør
Carbone, Paris
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 57 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
v. 2.44.0