activity
20192022
most citedR-GCN: The R Could Stand for Random

5 citations · 13 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG20221 cited

Perfectly predicting ICU length of stay: too good to be true

Sandeep Ramachandra, Gilles Vandewiele, David Vander Mijnsbrugge +2

A paper of Alsinglawi et al was recently accepted and published in Scientific Reports. In this paper, the authors aim to predict length of stay (LOS), discretized into either long…

cs.LG20224 cited

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

Gilles Vandewiele, Bram Steenwinckel, Terencio Agozzino +1

This paper introduces pyRDF2Vec, a Python software package that reimplements the well-known RDF2Vec algorithm along with several of its extensions. By making the algorithm availabl…

cs.LG20225 cited

R-GCN: The R Could Stand for Random

Vic Degraeve, Gilles Vandewiele, Femke Ongenae +1

The inception of the Relational Graph Convolutional Network (R-GCN) marked a milestone in the Semantic Web domain as a widely cited method that generalises end-to-end hierarchical…

cs.LG20203 cited

Walk Extraction Strategies for Node Embeddings with RDF2Vec in Knowledge Graphs

Gilles Vandewiele, Bram Steenwinckel, Pieter Bonte +5

As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that ca…

eess.SP2020

Overly Optimistic Prediction Results on Imbalanced Data: a Case Study of Flaws and Benefits when Applying Over-sampling

Gilles Vandewiele, Isabelle Dehaene, György Kovács +9

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Rece…

cs.NE2019

GENDIS: GENetic DIscovery of Shapelets

Gilles Vandewiele, Femke Ongenae, Filip De Turck

In the time series classification domain, shapelets are small time series that are discriminative for a certain class. It has been shown that classifiers are able to achieve state-…