Nurbek Tastan

nurbek.tastan@mbzuai.ac.ae

Abu Dhabi, UAE

I am Nurbek Tastan, currently pursuing a Doctor of Philosophy degree in Machine Learning. I am associated with the SPriNT-AI lab at MBZUAI, where I conduct my research under the guidance of my supervisors, Dr. Karthik Nandakumar and Dr. Samuel Horvath.

My research focuses on trustworthy federated learning, with particular emphasis on fairness, privacy, efficiency, and robustness in collaborative settings. I also develop methods to make large-scale models, including language models, more efficiently fine-tunable while also preserving utility and user confidentiality.

Passionate about building machine learning systems that are not only performant, but also equitable, privacy-aware, and computationally viable for real-world deployment.

selected publications

ICML

Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks

Nurbek Tastan, Samuel Horváth, and Karthik Nandakumar

In Proceedings of the Forty-second International Conference on Machine Learning (ICML) , 2025

Bib

@inproceedings{tastan2025aequa,
  title = {{Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks}},
  author = {Tastan, Nurbek and Horv\'{a}th, Samuel and Nandakumar, Karthik},
  year = {2025},
  url = {https://openreview.net/forum?id=Tw81RElDpe},
  booktitle = {Proceedings of the Forty-second International Conference on Machine Learning (ICML)},
  series = {Proceedings of Machine Learning Research},
}

ICLR

A Framework for Double-Blind Federated Adaptation of Foundation Models

Nurbek Tastan, and Karthik Nandakumar

In ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning (MCDC), Under Review at ICCV , 2025

Bib Poster

@inproceedings{tastan2025framework,
  title = {{A Framework for Double-Blind Federated Adaptation of Foundation Models}},
  author = {Tastan, Nurbek and Nandakumar, Karthik},
  booktitle = {ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning (MCDC), Under Review at ICCV},
  year = {2025},
  url = {https://openreview.net/forum?id=stv0Fqxekz},
}

CPAL

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning

Nurbek Tastan, Samuel Horváth, Martin Takáč, and Karthik Nandakumar

In The Second Conference on Parsimony and Learning (Proceedings Track) , Mar 2025

Bib Code Poster Project Page

@inproceedings{tastan2025fedpews,
  title = {Fed{PeWS}: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning},
  author = {Tastan, Nurbek and Horv{\'a}th, Samuel and Tak{\'a}{\v{c}}, Martin and Nandakumar, Karthik},
  booktitle = {The Second Conference on Parsimony and Learning (Proceedings Track)},
  year = {2025},
  month = mar,
  url = {https://openreview.net/forum?id=iYwiyS1YdQ},
  series = {Proceedings of Machine Learning Research},
}

CVPR

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss

Nurbek Tastan, and Karthik Nandakumar

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Jun 2023

Bib Code Poster Project Page

@inproceedings{tastan2023capride,
  author = {Tastan, Nurbek and Nandakumar, Karthik},
  title = {CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2023},
  pages = {8084-8092},
}

IJCAI
Redefining Contributions: Shapley-Driven Federated Learning

Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horvath, and Karthik Nandakumar

In International Joint Conference on Artificial Intelligence (IJCAI) , Aug 2024

Abs Bib Code Poster Project Page

Federated learning (FL) has emerged as a pivotal approach in machine learning, enabling multiple participants to collaboratively train a global model without sharing raw data. While FL finds applications in various domains such as healthcare and finance, it is challenging to ensure global model convergence when participants do not contribute equally and/or honestly. To overcome this challenge, principled mechanisms are required to evaluate the contributions made by individual participants in the FL setting. Existing solutions for contribution assessment rely on general accuracy evaluation, often failing to capture nuanced dynamics and class-specific influences. This paper proposes a novel contribution assessment method called ShapFed for fine-grained evaluation of participant contributions in FL. Our approach uses Shapley values from cooperative game theory to provide a granular understanding of class-specific influences. Based on ShapFed, we introduce a weighted aggregation method called ShapFed-WA, which outperforms conventional federated averaging, especially in class-imbalanced scenarios. Personalizing participant updates based on their contributions further enhances collaborative fairness by delivering differentiated models commensurate with the participant contributions. Experiments on CIFAR-10, Chest X-Ray, and Fed-ISIC2019 datasets demonstrate the effectiveness of our approach in improving utility, efficiency, and fairness in FL systems.
@inproceedings{tastan2024redefining, author = {Tastan, Nurbek and Fares, Samar and Aremu, Toluwani and Horvath, Samuel and Nandakumar, Karthik}, title = {Redefining Contributions: Shapley-Driven Federated Learning}, booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)}, year = {2024}, month = aug, }