Megha Khosla
Assistant Professor, Delft University of Technology (TU Delft)
Van Mourik Broekmanweg 6
2628 XE Delft
The Netherlands
I am an Assistant Professor in the Multimedia Computing Group in the Intelligent Systems Department at TU Delft. My primary area of research is machine learning on graph structured data. In particular, my research is dedicated to the development of cutting-edge algorithms that facilitate effective, interpretable, and privacy-preserving machine learning on graph data. I am currently spearheading a novel research line focused on exploring the intricate relationship between explainability and privacy in graph machine learning. Prior to my being a faculty member at TUD, I was a senior researcher at the L3S Research Centre, and the Leibniz University Hannover. I have also managed several collaborative projects both in Academia and in the industry where I spent a three-year stint after my PhD. I completed my PhD from the Max Planck Institute for Informatics (MPII), in Algorithms and the Complexity group, Saarbruecken, Germany.
news
Mar 5, 2024 | I led the successful organization (together with Delft Design for Values Institute) of the first workshop on the interplay of explainability and privacy held on 8th and 9th February, 2024. You can access the talk slides here |
---|---|
Sep 22, 2023 | Check out my tutorial (together with Luis Galárraga ) on Explainable GraphML presented at ECML 2023 |
Jul 13, 2023 | My first PhD student Ngan Thi Dong defended her PhD thesis on Joint learning from multiple information sources for biological problems Check out her amazing work! |
selected publications
-
Releasing graph neural networks with differential privacy guaranteesIn Transactions on Machine Learning Research 2023
-
Multi-label Node Classification On Graph-Structured DataIn Transactions on Machine Learning Research 2023
-
Private Graph Extraction via Feature ExplanationsIn Proceedings of Privacy Enhancing Technologies Symposium (PETS 2023) 2023
-
A message passing framework with multiple data integration for miRNA-disease association predictionNature Scientific Reports 2022
-
ZORRO: Valid, Sparse, and Stable Explanations in Graph Neural NetworksIEEE Transactions on Knowledge and Data Engineering 2022