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. Specifically, I develop algorithms to enable effective, interpretable, and privacy preserving learning on graphs. Prior to my being a faculty member at TUD, I was a senior research 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
May 25, 2022 | MuCoMiD: A Multitask graph Convolutional Learning Framework for miRNA-Disease Association Prediction with Ngan Dong and Stefanie Mücke is now accepted for publication in IEEE/ACM Transactions of Computational Biology and Bioinformatics. |
---|---|
Dec 15, 2021 | Our paper Membership Inference Attack on Graph Neural Networks together with Emmanuel Iyiola and Wolfgang Nejdl won the best student paper award at IEEE TPS 2021. |
selected publications
-
A message passing framework with multiple data integration for miRNA-disease association predictionScientific Reports 2022
-
ZORRO: Valid, Sparse, and Stable Explanations in Graph Neural NetworksIEEE Transactions on Knowledge and Data Engineering 2022
-
A multitask transfer learning framework for the prediction of virus-human protein-protein interactionsBMC Bioinform. 2021
-
A Comparative Study for Unsupervised Network Representation LearningIEEE Trans. Knowl. Data Eng. 2021
-
Membership Inference Attack on Graph Neural NetworksIn IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, (TPS-ISA) 2021
-
Node Representation Learning for Directed GraphsIn Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part I 2019