About me

I am a Ph.D. candidate at the University of Maryland (UMD), College Park,  currently conducting research in the Foundations of Reliable Machine Learning Lab (FORMAL) under the supervision of Prof. Sanghamitra Dutta. My research focuses on Trustworthy and Reliable Machine Learning, with an emphasis on Explainability, Robustness, and Fairness. Last summer, I worked as a AI research intern at JPMorgan AI Research, focusing on improving the reliability of large language models (LLMs) in critical high-stakes applications. 

Prior to joining UMD Electrical and Computer Engineering, I graduated summa cum laude (High Honors) with a B.Sc. in Electrical and Electronics Engineering from Isik University, Istanbul, Turkey, where I was the overall best-graduating student and Valedictorian for the class of 2020 (GPA: 3.98/4.00).

At UMD, I'm a co-recipient of the 2022-2023 George Corcoran Memorial Award for excellence in teaching. The 2022 Outstanding Teaching Assistant (TA) award, and will be serving as an Electrical and Computer Engineering TA Training and Development (TATD) Fellow for the 2022-2024 academic year, a program aimed at creating a cohort of leaders in the TA community. 

Research Interests

• Trustworthy/ Reliable Machine Learning

• Algorithmic Fairness

• Explainability 

• Privacy

• Information Theory

Publications

Updated list of my publications on Google Scholar.  

Conference Publications

• F. Hamman,  S. Dutta,  "Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition," International Conference on Learning Representations (ICLR 2024).          (Also Spotlight Talk ✨ at ISIT 2024 Workshop on Information-Theoretic Methods for Trustworthy Machine Learning)         (Also Invited to feature in Montreal AI Ethics Brief)

• F. Hamman,  S. Dutta,  "A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition,"  IEEE International Symposium on Information Theory (ISIT 2024). 

•  F. Hamman, E. Noorani, S. Mishra, D. Magazzeni, S. Dutta, "Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees," In: International Conference on Machine Learning (ICML 2023).

• F. Hamman, J. Chen, S. Dutta, “Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity,” In: ACM Conference on Fairness, Accountability, and Transparency (FAccT 2023) | Previously in NeurIPS 2022 Algorithmic Fairness through the Lens of Causality and Privacy Workshop. 

• P. Dissanayake,  F. Hamman, B. Halder, Q. Zhang, I. Sucholutsky, S. Dutta, “Quantifying Knowledge Distillation using Partial Information Decomposition,” Accepted at the International Conference on Artificial Intelligence and Statistics (AISTATS 2025).

• E. Noorani, P. Dissanayake, F. Hamman, S. Dutta. “Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures.”Accepted at International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025).

Journal Publications 

• F. Hamman, E. Noorani, S. Mishra, D. Magazzeni, and S. Dutta, "Robust Algorithmic Recourse Under Model Multiplicity with Probabilistic Guarantees,” Journal on Selected Areas in Information Theory: Information-Theoretic Methods for Trustworthy Machine Learning (JSAIT 2024).

• S. Dutta,  F. Hamman, "A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability, "  Entropy Journal: Information Theory, Probability, and Statistics. Special Issue: Fairness in Machine Learning, 2023.

Other Papers (Peer-Reviewed Workshops/Preprints)

• F. Hamman, P. Dissanayake, S. Mishra, F. Lecue, S. Dutta, "Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs”, Workshop on Explainability in LLMs at JPMC and Imperial College London.

• F. Hamman,  S. Dutta,  "Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Information Theory," In: Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities Workshop at ICML 2023. (Also Invited to feature in Montreal AI Ethics Brief)

• B. Halder, F. Hamman, P. Dissanayake, Q. Zhang, I. Sucholutsky, S. Dutta, "Quantifying Spuriousness of Biased Datasets Using Partial Information Decomposition,"  Workshop on Data-centric ML Research: Datasets for Foundation Models, ICML 2024. 

• P. Dissanayake, F. Hamman, B. Halder, Q. Zhang, I. Sucholutsky, S. Dutta, "Formalizing Limits of Knowledge Distillation Using Partial Information Decomposition,"  Machine Learning and Compression Workshop, Neurips 2024.

Services & Outreach

• Co-organizer for AI Alignment Workshop at UMD

• Reviewer ICLR 2024 conference.

• Reviewer for ICAIF Workshop on Explainable AI in Finance 2023

• Volunteer ICML 2023 conference.

• Reviewer for NeurIPS 2023.

• Serving as a Reviewer on the Program Committee for the 2023 Fairness, Accountability, and Transparency FAccT conference.

• Reviewer for  NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Privacy AFCP2022.

• Student volunteer at  FAccT 2022 conference.

Education

• Ph.D/MS. In Electrical and Computer Engineering at the University of Maryland, College Park, USA (2020 - present)

• B.Sc.  in Electrical and Electronics Engineering at Isik University, Istanbul, Turkey. 

GPA: 3.98/4.00 (2016 - 2020)