- Ph.D., Computer, Communication and Information Sciences (2011-2016), Thesis title: “Network Alignment: Theory, Algorithms, and Applications”, Laboratory for computer Communications and Applications (LCA4), EPFL, Lausanne, Switzerland.
- Ph.D. candidate, Computer, Communication and Information Sciences (2010-2011), Unaffiliated Ph.D. student, EPFL, Lausanne, Switzerland, Laboratory for computer Communications and Applications (LCA1).
- MS.c., Electrical Engineering and Communication Systems (2008-2010), Sharif University of Technology, Tehran, Iran.
- BS.c., Electrical Engineering and Communication Systems (2004-2008), Sharif University of Technology, Tehran, Iran.
- Submodular optimization: In this project, we studied the problem of scalable submodular maximization under the unifying umbrella of robust computation, where the dataset may change over time (i.e., some portion of data or sensitive features are deleted) or the utility function is not fully known.
- Deep learning in computational biology: We utilized several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer and classify the morphological quality of blastocysts.
- Fairness in machine learning: Nowadays, many sensitive decision-making tasks rely on predictions from automated statistical and machine learning algorithms. In this project, we answered the question of how to control for latent discrimination in predictive models and how to provably remove it.
- Network alignment: In this project, the goal was to merge information from different sources where the data provides two (or more) partial views of the network, and where the node labels are sometimes ambiguous. We studied this problem form information theoretic, algorithmic and application perspectives.
- Mobility modeling and location privacy: The goal was to model the mobility from individual and collective perspectives. We also investigated the privacy of users for a location-based service system based on the mobility of users.
- Soheil Ghili, Ehsan Kazemi, and Amin Karbasi. Eliminating Latent Discrimination: Train Then Mask. AAAI, 2019 (oral presentation). [poster]
- Moran Feldman, Amin Karbasi, and Ehsan Kazemi. Do Less, Get More: Streaming Submodular Maximization with Subsampling. NeurIPS, 2018 (spotlight presentation). [slides] [poster] [video]
- Pegah Khosravi, Ehsan Kazemi, Qiansheng Zhan, Marco Toschi, Jonas E Malmsten, Cristina Hickman, Marcos Meseguer, Zev Rosenwaks, Olivier Elemento, Nikica Zaninovic, and Iman Hajirasouliha. Robust Automated Assessment of Human Blastocyst Quality using Deep Learning. bioRxiv, 2018. [Accepted with a minor revision to npj Digital Medicine-Nature]
- Ehsan Kazemi, Morteza Zadimoghaddam, and Amin Karbasi. Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints. ICML, 2018. [slides] [poster]
- Marko Mitrovic, Ehsan Kazemi, Morteza Zadimoghaddam, and Amin Karbasi. Data Summarization at Scale: A Two-Stage Submodular Approach. ICML, 2018. [poster]
- Ehsan Kazemi and Matthias Grossglauser. MPGM: Scalable and Accurate Multiple Network Alignment. arXiv preprint arXiv:1804.10029, 2018. Accepted to IEEE/ACM Transactions on Computational Biology and Bioinformatics.
- Ehsan Kazemi, Lin Chen, Sanjoy Dasgupta, and A. Karbasi. Comparison Based Learning from Weak Oracles. AISTATS, 2018. [slides] [poster]
- Pegah Khosravi, Ehsan Kazemi, Marcin Imielinski, Olivier Elemento, and Iman Hajirasouliha. Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images. EBioMedicine, 2017. [poster] [code]
- Ehsan Kazemi, Hamed Hassani, Matthias Grossglauser, and Hassan Pezeshghi Modarres. PROPER: Global Protein Interaction Network Alignment through Percolation Matching. BMC Bioinformatics, 2016. Website: http://proper.epfl.ch/
- Ehsan Kazemi and Matthias Grossglauser. On the Structure and Efficient Computation of IsoRank Node Similarities. arXiv preprint arXiv:1602.00668, 2016.
- Ehsan Kazemi, Hamed Hassani, and Matthias Grossglauser. Growing a Graph Matching from a Handful of Seeds. VLDB, 2015. [slides] [poster]
- Ehsan Kazemi, Lyudmila Yartseva, and Matthias Grossglauser. When Can Two Unlabeled Networks Be Aligned under Partial Overlap? Annual Allerton Conference on Communication, Control, and Computing, 2015. [slides]
- Reza Shokri, George Theodorakopoulos, Panos Papadimitratos, Ehsan Kazemi, and Jean-Pierre Hubaux. Hiding in the mobile crowd: Location privacy through collaboration. IEEE Transactions on Dependable and Secure Computing, 2014.
- Mohamed Kafsi, Ehsan Kazemi, Lucas Maystre, Lyudmila Yartseva, Matthias Grossglauser, and Patrick Thiran. Mitigating Epidemics through Mobile Micro-Measures. Third International Conference on the Analysis of Mobile Phone Datasets, 2013. [poster]
- Vincent Etter, Mohamed Kafsi, Ehsan Kazemi, Matthias Grossglauser, and Patrick Thiran. Where to Go from Here? Mobility Prediction from Instantaneous Information. Pervasive and Mobile Computing, 2013.
- Vincent Etter, Mohamed Kafsi, and Ehsan Kazemi. Been There, Done That: What Your Mobility Traces Reveal about Your Behavior. Mobile Data Challenge by Nokia Workshop, in conjunction with Int. Conf. on Pervasive Computing, 2012. [poster]