Research

Research interests and goals

My research aims to study how machine learning systems encode values, assumptions, and trade-offs, and how these choices affect different individuals and groups in practice. I am interested in fairness, privacy, and accountability, particularly in settings where objectives, data, or stakeholders are heterogeneous. Rather than treating ethical or technical criteria as fixed, my work examines how problem formulations and evaluation choices shape outcomes and harms. I combine empirical and conceptual approaches to better understand the limits of current ML methods and to support more responsible, context-aware AI development.

For the full list of papers, see my Google scholar profile..

Selected publications

Ganesh, P., Taïk, A., & Farnadi, G. (2025). Systemizing multiplicity: The curious case of arbitrariness in machine learning. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025).

Chehbouni, K., De Cock, M., Caporossi, G., Taïk, A., Rabbany, R., & Farnadi, G. (2025). Enhancing privacy in the early detection of sexual predators through federated learning and differential privacy. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2025).

Taïk, A., Chehbouni, K., & Farnadi, G. (2025). Fairness in federated learning: Fairness for whom? In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025).

Chatagner, C., Ma, R., Ganesh, P., Taïk, A., Creager, E., & Farnadi, G. (2025). Say it another way: Auditing LLMs with a user-grounded automated paraphrasing framework. arXiv preprint.

Malekmohammadi, S., Taïk, A., & Farnadi, G. (2024). Differentially private clustered federated learning. Transactions on Machine Learning Research (TMLR).

Neophytou, N., Taïk, A., & Farnadi, G. (2024). Promoting fair vaccination strategies through influence maximization: A case study on COVID-19 spread. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2024).

Chehbouni, K., Roshan, M., Ma, E., Wei, F. A., Taïk, A., Cheung, J. C. K., & Farnadi, G. (2024). From representational harms to quality-of-service harms: A case study on Llama 2 safety safeguards. In Findings of the Association for Computational Linguistics (ACL 2024), 15694–15710.

Molamohammadi, M., Taïk, A., Roux, N. L., & Farnadi, G. (2023). Unraveling the interconnected axes of heterogeneity in machine learning for democratic and inclusive advancements. In Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO 2023).

Taïk, A., Mlika, Z., & Cherkaoui, S. (2022). Clustered vehicular federated learning: Process and optimization. IEEE Transactions on Intelligent Transportation Systems.

Abouaomar, A., Taïk, A., Filali, A., & Cherkaoui, S. (2022). Federated deep reinforcement learning for Open RAN slicing in 6G networks. IEEE Communications Magazine.

Taïk, A., Mlika, Z., & Cherkaoui, S. (2021). Data-aware device scheduling for federated edge learning. IEEE Transactions on Cognitive Communications and Networking.

Taïk, A., & Cherkaoui, S. (2020). Electrical load forecasting using edge computing and federated learning. In Proceedings of the IEEE International Conference on Communications (ICC 2020), 1–6.

Taïk, A., & Cherkaoui, S. (2020). Federated edge learning: Design issues and challenges. IEEE Network, 35(2), 252–258.