Scholar
Megha Khosla
Google Scholar ID: sn4Ycm0AAAAJ
Assistant Professor at TU Delft
Citations & Impact
Citations
1,314
H-index
19
i10-index
26
Publications
20
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including:
- - Disentangled and Self-Explainable Node Representation Learning (TMLR 2025)
- - Dine: Dimensional interpretability of node embeddings (IEEE Transactions on Knowledge and Data Engineering, 2024)
- - Multi-label Node Classification On Graph-Structured Data (Transactions on Machine Learning Research, 2023)
- - Private Graph Extraction via Feature Explanations (PETS 2023)
- - A message passing framework with multiple data integration for miRNA-disease association prediction (Nature Scientific Reports, 2022)
- - ZORRO: Valid, Sparse, and Stable Explanations in Graph Neural Networks (IEEE Transactions on Knowledge and Data Engineering, 2022)
Research Experience
- She was a senior researcher at the L3S Research Centre and Leibniz University Hannover. She has managed several collaborative projects both in academia and industry.
Education
- Completed her PhD from the Max Planck Institute for Informatics (MPII), in Algorithms and the Complexity group, Saarbruecken, Germany.
Background
- Currently an Assistant Professor in the Multimedia Computing Group at TU Delft, her primary area of research is machine learning on graph structured data. Her research focuses on developing effective, interpretable, and privacy-preserving machine learning algorithms. She is also leading a new research line that explores the intricate relationship between explainability and privacy in machine learning.
Miscellany
- Personal interests and other information not provided.
