Aleksandar Bojchevski
Scholar

Aleksandar Bojchevski

Google Scholar ID: F1APiN4AAAAJ
University of Cologne
Machine LearningGraphs/NetworksTrustworthyRobustnessUncertainty
Citations & Impact
All-time
Citations
7,669
 
H-index
22
 
i10-index
30
 
Publications
20
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Paper 'SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors' accepted at NeurIPS 2024
  • Paper on robust conformal prediction accepted at ICML 2024
  • Two papers accepted at ICLR 2024: one on label poisoning and one on conformal GNNs
  • Two papers accepted at NeurIPS 2023: one on certificates and one on GATs
  • Paper 'Conformal Prediction Sets for Graph Neural Networks' accepted at ICML 2023
  • Co-authored paper 'Are Defenses for Graph Neural Networks Robust?' accepted at NeurIPS 2022
  • Received a teaching award for the Machine Learning lecture (SS 24) in January 2025
Research Experience
  • Currently full professor at the University of Cologne, leading the Trustworthy AI research group
  • Previously faculty at CISPA Helmholtz Center for Information Security
  • Joined the Center for Data and Simulation Science at the University of Cologne as a core scientist in September 2023
  • Co-organized the seminar series 'Next Generation Graph Neural Networks' with colleagues from University of Cologne and RWTH Aachen
  • Co-organizing the 'Learning on Graphs Meet Up' with RWTH Aachen colleagues