Nezihe Merve Gürel

PhD candidate at ETH Zurich


STF H 322

Stampfenbachstrasse 114

8092 Zurich Switzerland

I am a PhD candidate within the Systems Group in the Department of Computer Science at ETH Zurich supervised by Prof. Ce Zhang. My research goal is to form a principled understanding of many aspects of MLSys: from hardware to label efficiency and robustness, and moreover using this knowledge, I aim to build theoretically-sound, usable, robust and scalable machine learning systems.

Prior to my PhD journey, I obtained my masters from the School of Computer and Communication Sciences at EPFL, where I was a research scholar at the Information Theory Laboratory. There I worked on topics of advanced probability and information theory such as convergence rates of bounded martingales and rate-distortion theory. During and after my masters, I was also a researcher at IBM Research in Zurich, and worked on building denoising algorithms for modern radio telescopes.


Jun 15, 2021 I have been named one of the recipients for 2021 Google Scholarships!
May 19, 2021 Knowledge Enhanced Machine Learning Pipeline Against Adversarial Attacks accepted at ICML 2021.
May 19, 2021 DeGNN: Improving Graph Neural Networks with Graph Decomposition and Interactive Feature Generation via Learning Adjacency Tensor of Feature Graph accepted at KDD 2021.
Apr 15, 2021 Online Active Model Selection for Pre-trained Classifiers presented at AISTATS 2021.


    • Reviewer NeurIPS {2022, 2021, 2020}, ICML 2022, AISTATS {2022, 2021, 2020}, ICLR 2022
    • Workshops Area Chair: ITR3@ICML2021, Organizer: WiML@NeurIPS2019
    • Misc WiML Board of Directors, Vice President