Ansatte – Københavns Universitet

Learning from graphs with structural variation

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

We study the effect of structural variation in graph data on the predictive performance
of graph kernels. To this end, we introduce a novel, noise-robust adaptation
of the GraphHopper kernel and validate it on benchmark data, obtaining modestly
improved predictive performance on a range of datasets. Next, we investigate the
performance of the state-of-the-art Weisfeiler-Lehman graph kernel under increasing
synthetic structural errors and find that the effect of introducing errors depends
strongly on the dataset.
OriginalsprogEngelsk
TitelNeural Information Processing Systems 2017
RedaktørerI. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, R. Garnett
Antal sider5
ForlagNIPS Proceedings
Publikationsdato2017
StatusUdgivet - 2017
Begivenhed31st Annual Conference on Neural Information Processing Systems - Long Beach, USA
Varighed: 4 dec. 20179 dec. 2017
Konferencens nummer: 31

Konference

Konference31st Annual Conference on Neural Information Processing Systems
Nummer31
LandUSA
ByLong Beach
Periode04/12/201709/12/2017
NavnAdvances in Neural Information Processing Systems
Vol/bind30
ISSN1049-5258

ID: 194814655