S
Sandra Mitrović
Researcher at Katholieke Universiteit Leuven
Publications - 25
Citations - 316
Sandra Mitrović is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Feature learning & Computer science. The author has an hindex of 6, co-authored 23 publications receiving 208 citations. Previous affiliations of Sandra Mitrović include Dalle Molle Institute for Artificial Intelligence Research & Max Planck Society.
Papers
More filters
Journal ArticleDOI
Machine-learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: The PS1 Sample
Branimir Sesar,Nina Hernitschek,Sandra Mitrović,Željko Ivezić,Hans-Walter Rix,Judith G. Cohen,Edouard J. Bernard,Eva K. Grebel,Nicolas F. Martin,Nicolas F. Martin,Edward F. Schlafly,Edward F. Schlafly,William S. Burgett,Peter W. Draper,H. Flewelling,Nick Kaiser,Rolf-Peter Kudritzki,Eugene A. Magnier,Nigel Metcalfe,John L. Tonry,C. Z. Waters +20 more
TL;DR: In this paper, a template fitting technique was used to identify RR Lyrae stars in the PanSTARRS1 (PS1) 3π survey, and the authors obtained accurate period estimates, precise to 2 s in >80% of cases.
Proceedings ArticleDOI
Combining temporal aspects of dynamic networks with Node2Vec for a more efficient dynamic link prediction
TL;DR: This work aims at extending node2vec, representation learning method successfully applied for static link prediction, to a dynamic setup and results show that taking into account dynamic aspect outperforms static approach.
Journal ArticleDOI
On the operational efficiency of different feature types for telco Churn prediction
TL;DR: This work bridges the gap between predictive performance and operational efficiency by devising a new feature type classification and a novel reusable method to determine optimal feature type combinations based on Pareto multi-criteria optimization.
Book ChapterDOI
AngryBERT: Joint Learning Target and Emotion for Hate Speech Detection
TL;DR: AngryBERT as discussed by the authors proposes a novel multitask learning-based model, which jointly learns hate speech detection with sentiment classification and target identification as secondary relevant tasks, which outperforms state-of-the-art single-task learning baselines.
Journal ArticleDOI
tcc2vec: RFM-informed representation learning on call graphs for churn prediction
TL;DR: In this paper, the authors propose tcc2vec, a panoptic approach aiming at devising representation learning on enriched call networks that integrate interaction and structural information, which are being sliced in different time periods in order to account for different temporal granularities.