Dr Baturalp Buyukates PhD

Dr Baturalp Buyukates

School of Computer Science
Assistant Professor in Computer Science

Contact details

Address
School of Computer Science
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK

Dr Buyukates is an Assistant Professor at the School of Computer Science.

His research interests span privacy-preserving machine learning, reliable generative AI, human-centred computing, distributed systems, communications, networks, and information theory.

Find more about Baturalp’s research on his personal webpage.

Qualifications

  • PhD in Electrical Engineering, University of Maryland, 2022
  • MSc in Electrical Engineering, University of Maryland, 2020
  • BSc in Electrical and Electronics Engineering, Bilkent University, 2016

Biography

Dr Baturalp Buyukates is an Assistant Professor at the University of Birmingham, where he is part of the Socio-Technical Systems group within the School of Computer Science. Previously, he was a postdoctoral research associate at the University of Southern California, working with Salman Avestimehr. He earned his MSc and PhD degrees in Electrical Engineering from the University of Maryland, College Park, in 2020 and 2022, respectively, under the supervision of Sennur Ulukus. Prior to that, he completed his BSc in Electrical and Electronics Engineering at Bilkent University, Turkey, in 2016.

His research interests span machine learning, generative artificial intelligence, human-centred computing, distributed systems, wireless communications, networks, and information theory. His current research focuses on reliable and explainable large language models (LLMs), privacy-preserving machine learning, responsible data economics for collaborative machine learning, timely information exchange in distributed systems, and the semantics of information.

He received the 2024 CTTC Andrea Goldsmith Young Scholars Award for his contributions to age of information, low-latency communications, distributed computation, and learning. His work has received multiple best paper recognitions, and he was awarded the George Harhalakis Outstanding Graduate Student Award from the Institute for Systems Research at the University of Maryland in 2021 for his doctoral research on timely information delivery in large networks, distributed computation, and machine learning.

In his highly interdisciplinary research, Dr Buyukates utilizes tools and techniques from optimization, machine learning, statistics, applied cryptography, and information and coding theories.

Teaching

  • LC Artificial Intelligence 1, Computer Science

Postgraduate supervision

Accepting PhD applications in the general areas of Machine Learning (ML) Safety, Trustworthy Generative Artificial Intelligence (AI), Human-Centred Computing, Distributed Systems, Wireless Communications, Networks, and Information Theory. See the recent projects in the Research tab.

Research

Key Focus Areas:

  1. Reliable and Explainable LLMs/VLMs – Ensuring large language and vision language models are robust, transparent, and trustworthy.
  2. Continual Learning for LLMs – Developing models that adapt to new information without forgetting prior knowledge.
  3. Multi-Agent AI Systems – Enhancing coordination, routing, and learning among multiple AI agents in dynamic, heterogeneous environments.
  4. Privacy-Preserving Training/Finetuning of Foundation Models – Protecting user data while training large models.
  5. Trustworthy Federated/Collaborative Learning – Building frameworks that ensure integrity, verifiability, and security for collaborative learning.
  6. Responsible Data Economics – Exploring ethical ways to assess data value and ownership in AI ecosystems.
  7. AI-Driven Goal-Oriented Communication Networks – Applying AI tools to enhance the efficiency and adaptability of future time-sensitive networks.

Publications

Recent publications

Article

Buyukates, B, So, J, Mahdavifar, H & Avestimehr, S 2024, 'LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning', IEEE Journal on Selected Areas in Information Theory, vol. 5, pp. 285-301. https://doi.org/10.1109/JSAIT.2024.3391849

Buyukates, B, Ozfatura, E, Ulukus, S & Gündüz, D 2023, 'Gradient Coding With Dynamic Clustering for Straggler-Tolerant Distributed Learning', IEEE Transactions on Communications, vol. 71, no. 6, pp. 3317-3332. https://doi.org/10.1109/TCOMM.2022.3166902

Buyukates, B, Bastopcu, M & Ulukus, S 2022, 'Version Age of Information in Clustered Gossip Networks', IEEE Journal on Selected Areas in Information Theory, vol. 3, no. 1, pp. 85-97. https://doi.org/10.1109/JSAIT.2022.3159745

Comment/debate

Buyukates, B, So, J, Mahdavifar, H & Avestimehr, S 2024, 'Erratum to “LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning”', IEEE Journal on Selected Areas in Information Theory, vol. 5, pp. 570-571. https://doi.org/10.1109/JSAIT.2024.3413928

Conference contribution

Ziashahabi, A, Buyukates, B, Sheshmani, A, You, Y-Z & Avestimehr, S 2024, Frequency Domain Diffusion Model with Scale-Dependent Noise Schedule. in 2024 IEEE International Symposium on Information Theory (ISIT). IEEE International Symposium on Information Theory, IEEE, pp. 19-24, 2024 IEEE International Symposium on Information Theory (ISIT), Athens, Greece, 7/07/24. https://doi.org/10.1109/ISIT57864.2024.10619452

Bakman, YF, Yaldiz, DN, Buyukates, B, Avestimehr, S, Tao, C & Dimitriadis, D 2024, Predicting Uncertainty of Generative LLMs with MARS: Meaning-Aware Response Scoring. in 2024 IEEE International Symposium on Information Theory (ISIT). IEEE International Symposium on Information Theory, IEEE, pp. 2033-2037, 2024 IEEE International Symposium on Information Theory (ISIT), Athens, Greece, 7/07/24. https://doi.org/10.1109/ISIT57864.2024.10619136

Buyukates, B, He, C, Han, S, Fang, Z, Zhang, Y, Long, J, Farahanchi, A & Avestimehr, S 2023, Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchain. in 2023 IEEE International Conference on Decentralized Applications and Infrastructures (DAPPS). IEEE International Conference on Decentralized Applications and Infrastructures, IEEE, pp. 13-22, 2023 IEEE International Conference on Decentralized Applications and Infrastructures (DAPPS), Athens, Greece, 17/07/23. https://doi.org/10.1109/DAPPS57946.2023.00012

Bastopcu, M, Buyukates, B & Ulukus, S 2022, Gossiping with Binary Freshness Metric. in 2021 IEEE Globecom Workshops (GC Wkshps)., 9682174, IEEE Globecom Workshop, IEEE, 2021 IEEE Globecom Workshops (GC Wkshps), 7/12/21. https://doi.org/10.1109/GCWkshps52748.2021.9682174

Preprint

Yaldiz, DN, Bakman, YF, Buyukates, B, Tao, C, Ramakrishna, A, Dimitriadis, D & Avestimehr, S 2024 'Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs' arXiv, pp. 1-16. https://doi.org/10.48550/arXiv.2406.11278

Bakman, YF, Yaldiz, DN, Buyukates, B, Tao, C, Dimitriadis, D & Avestimehr, S 2024 'MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs' arXiv, pp. 1-16. https://doi.org/10.48550/arXiv.2402.11756

Yang, M, Jarin, I, Buyukates, B, Avestimehr, S & Markopoulou, A 2024 'Maverick-Aware Shapley Valuation for Client Selection in Federated Learning' arXiv, pp. 1-8. https://doi.org/10.48550/arXiv.2405.12590

Sheshmani, A, You, Y-Z, Buyukates, B, Ziashahabi, A & Avestimehr, S 2024 'Renormalization Group flow, Optimal Transport and Diffusion-based Generative Model' arXiv. https://doi.org/10.48550/arXiv.2402.17090

Han, S, Buyukates, B, Hu, Z, Jin, H, Jin, W, Sun, L, Wang, X, Wu, W, Xie, C, Yao, Y, Zhang, K, Zhang, Q, Zhang, Y, Joe-Wong, C, Avestimehr, S & He, C 2023 'FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs' arXiv, pp. 1-12. https://doi.org/10.48550/arXiv.2306.04959

Han, S, Wu, W, Buyukates, B, Jin, W, Zhang, Q, Yao, Y, Avestimehr, S & He, C 2023 'Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification' arXiv, pp. 1-17. https://doi.org/10.48550/arXiv.2310.04055

Li, S, Hou, S, Buyukates, B & Avestimehr, S 2022 'Secure Federated Clustering' arXiv, pp. 1-20. https://doi.org/10.48550/arXiv.2205.15564

View all publications in research portal