Research

Our research goal is to develop robust and reliable machine learning strategies with high reasoning capabilities. We aim to achieve this by enhancing the quality of the data, referred to as data-centric ML research, and integrating human expertise and logical reasoning into data-driven strategies as relying solely on data-driven methods may not always yield dependable and trustworthy outcomes. Presented below is a set of selected papers, and you can find a list of all publications here.

Selected publications

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

arXiv preprint 2023

Patrik Okanovic, Roger Waleffe, Vasilis Mageirakos, Konstantinos E Nikolakakis, Amin Karbasi, Dionysis Kalogerias, Nezihe Merve Gürel, Theodoros Rekatsinas

https://arxiv.org/abs/2305.18424

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks

International Conference on Machine Learning 2021

Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li

http://proceedings.mlr.press/v139/gurel21a

DeGNN Improving Graph Neural Networks with Graph Decomposition

ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2021

Xupeng Miao*, Nezihe Merve Gürel*, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Susie Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang

https://arxiv.org/pdf/1910.04499.pdf

Online Active Model Selection for Pre-trained Classifiers

International Conference on Artificial Intelligence and Statistics 2021

Nezihe Merve Gürel*, Mohammad Reza Karimi*, Bojan Karlaš, Johannes Rausch, Ce Zhang, Andreas Krause

http://proceedings.mlr.press/v130/reza-karimi21a/reza-karimi21a.pdf

Compressive Sensing Using Iterative Hard Thresholding with Low Precision Data Representation

IEEE Transactions on Signal Processing 2020

Nezihe Merve Gürel, Kaan Kara, Alen Stojanov, Tyler Smith, Thomas Lemmin, Dan Alistarh, Markus Püschel, Ce Zhang

https://arxiv.org/pdf/1802.04907.pdf

Efficient Task-specific Data Valuation for Nearest Neighbor Algorithms

International Conference on Very Large Data Bases 2019

Ruoxi Jia, David Dao, Boxin Wang, Frances Ann Hubis, Nezihe Merve Gürel, Bo Li, Ce Zhang, Costas J Spanos, Dawn Song

https://arxiv.org/abs/1908.08619