Dr. Mohamed Nafea
Assistant Professor, Electrical and Computer Engineering Department
Email: mnafea@mst.edu
Office: 131 Emerson Electric Co Hall;
Phone: (573) 341-4558
About Me
I am an Assistant Professor in Computer Engineering in the Electrical & Computer Engineering (ECE) department at Missouri University of Science & Technology. Before joining Missouri S&T, I was an Assistant Professor in the ECE department at University of Detroit. Prior to that, I spent a year as a postdoctoral research fellow at Georgia Tech, ECE.
I received my Ph.D. degree in electrical engineering from Penn State, University Park, in December 2018, under supervision of Aylin Yener. I also received a masters degree in mathematics from Penn State in 2017. Before that, I received a masters degree in wireless & information technologies from Nile University, Egypt, in 2012, and my bachelor degree in Electrical Engineering (communication and electronics specialization) from Alexandria University, Egypt, in 2010.
My research lies at the intersection of statistical learning, information and data sciences, and causal reasoning, and aims to solve problems in responsible development of machine learning models encompassing issues of reliability & trustworthiness, algorithmic fairness, explainability/interpretability, privacy, robustness and security. Specific areas of research interest include:
- Developing fair & explainable ML models; with emphasis on “representation learning” approaches.
- Federated learning & distributed optimization; with emphasis on privacy, fairness, and robustness.
- Causal reasoning & inference with applications to ML fairness & interpretability; social &biological sciences: econometrics.
- Developing ML diagnostic models for Healthcare applications, with emphasis on explainability,privacy, robustness, trustworthiness, and fairness.
- Statistical guarantees (e.g., conformal prediction, bounds & confidence intervals) for trustworthy,fair, and explainable ML models.
- Information theory; with emphasis on security & privacy of information processing systems.
On the application side, I am interested in a wide range of disciplines including information processing systems, image processing, data science, health informatics, as well as social, biological, and legal sciences.
Join US! I am always looking for talented and self-motivated PhD students to join our research group and work on subjects listed above. If you are interested, please check out this ad and apply accordingly.
If you are already a student at Missouri S&T, then taking a course that I am offering and doing very well is a great plus.
News!
- October 2024: Our paper “Causal Discovery in Linear Models with Unobserved Variables and Measurement Error” was accepted for presentation at the Causal Representation Learning workshop at the 2024 Neural Information Processing Conference (CRL@NeurIPS24)
- September 2024: Our paper “Centralized and Federated Heart Disease Classification Models Using UCI Dataset and their Shapley-value Based Intepretability” was accepted for publication at the ACM 8th International Conference on Advances in Artificial Intelligence (ICAAI 2024).
- August 2024: I started a new position as an Assistant Professor in Computer Engineering at Missouri University of Science & Technology, ECE department.
- August 2024: I was elevated to an IEEE senior member!
- August 24: My master’s student Mario Rodriguez has successfully defended his master’s thesis!
- July 2024: Our paper “Causal Discovery in Linear Models with Unobserved Variables and Measurement Error” is available on arXiv.
- May 2024: PhD student Sokrat Aldarmini joined our research group. Welcome Sokrat!
- April 2024: I delivered a virtual talk titled “Towards Responsible AI: Learning with Biased, Imperfect, and Decentralized Data” to the Computer Science Department at Texas Tech University.
- March 2024: I visited the ECE department at University of New Haven and delivered the same talk.
- February 2024: I visited the ECE department at Missouri University of Science and Technology and delivered the same talk.