Emir Ceyani
Ph.D. Student at vITAL Lab, President at USC TGSA, and Research Intern at FedML.ai


Recent News

I will be a student organizer at the 1st FedGraph Workshop!

Jun 2022

Reviewer for NeurIPS’22 Conference: Main and Dataset \& Benchmark Tracks!

Jun 2022

SpreadGNN accepted to AAAI’22 Conference!

Oct 2021

Short Bio

I am a Ph.D. student in Prof. Salman Avestimehr’s Information Theory and Machine Learning (vITAL) research lab at the University of Southern California (USC) in Los Angeles . I pursue research on the foundations and applications of federated learning, graph neural networks, probabilistic deep learning, and information theory. I seek to design learning algorithms that can effectively handle the non-I.I.D. nature of real-life data in federated setting. I try to actively contribute to FedML, a promising research library for federated learning as I believe that federated learning systems should be accessible for everyone. Previously, I was a Master’s student at Bilkent University, Ankara, Turkey, and an R&D engineer at Turkcell Technology under my master’s advisor, Dr. Salih Ergut with a prestigious 5G & Beyond Graduate Support Program.

Research Interests

Federated Learning Graph Neural Networks
Approximate Bayesian Inference Bayesian Deep Learning
Deep Probabilistic Generative Models Mathematical Foundations of Machine Learning


Ph.D. in Electrical & Computer Engineering
University of Southern California | Los Angeles, CA

Thesis Title: Federated Learning From Various Perspectives: Graphs, Physics, and Information
Advisor: Prof. Salman Avestimehr

Jan 2021 - Present
M.Sc. in Electrical & Electronics Engineering (High Honors)
Bilkent University | Ankara,TR

Thesis Title: Spatio-temporal Forecasting Over Graphs with Deep Learning
Advisor: Dr. Salih Ergut

Jun 2018 - Dec 2020
B.Sc. in Electrical & Electronics Engineering (High Honors)
Bilkent University | Ankara,TR
Sep 2013 - Jun 2018


Google Scholar

Semantic Scholar


Personalized, Federated, And Unified MRI Contrast Synthesis
O. Dalmaz, U. Mirza, G. Elmas, M. Özbey, S. Dar, E. Ceyani, S. Avestimehr, and T. Çukur
Published at the IEEE 20th International Symposium on Biomedical Imaging (ISBI), Virtual Conference 2023
[1] [pdf]


Federated Learning of Generative Image Priors for MRI Reconstruction
G. Elmas, S. Dar, Y. Korkmaz, E. Ceyani, B. Susam, M. Özbey, S. Avestimehr, and T. Çukur
Published at the IEEE Transactions on Medical Imaging 2022
[2] [pdf]
One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesis
O. Dalmaz, U. Mirza, G. Elmas, M. Özbey, S. Dar, E. Ceyani, S. Avestimehr, and T. Çukur
arXiv Preprint and Accepted at Medical Imaging meets NeurIPS Workshop 2022 2022
[3] [pdf]
pFLSynth: Personalized Federated Learning of Image Synthesis in Multi-Contrast MRI
O. Dalmaz, U. Mirza, G. Elmas, M. Özbey, S. Dar, E. Ceyani, S. Avestimehr, and T. Çukur
Accepted to NeurIPS Medical Imaging Meets as oral presentation 2022
[4] [pdf]


SpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data
C. He*, E. Ceyani*, K. Balasubramanian*, M. Annavaram, and S. Avestimehr
Published at the AAAI'22 (AR: 15% (1349/9020), poster), FL-ICML'21 & DLG-KDD'21. 2021
[5] [abs] [pdf] [code] [slide] [poster]
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
C. He*, K. Balasubramanian*, E. Ceyani*, C. Yang, H. Xie, L. Sun, L. He, L. Yang, P. Yu, Y. Rong, P. Zhao, J. Huang, M. Annavaram, and S. Avestimehr
Accepted to ICLR - DPML 2021 & MLSys - GNNSys'21. Collaborated with Tencent AI. 2021
[6] [abs] [pdf] [code] [slide] [poster] [video]


Spatio-temporal forecasting over graphs with deep learning
E. Ceyani
Bilkent 2020
[7] [abs] [pdf]


A highly efficient recurrent neural network architecture for data regression
T. Ergen and E. Ceyani
26th Signal Processing and Communications Applications Conference, SIU 2018, Izmir, Turkey 2018
[8] [pdf]

Previous Positions

Research Intern, FedML Inc., Los Angeles, CA

May 2022 - August 2022

5G VATS R&D Engineer, Turkcell Technology, Istanbul, TR

Oct 2018 - Dec 2020

Research & Teaching Assistant, Bilkent University, Ankara TR

Jun 2018 - Sep 2020

Honors & Awards

Full scholarship for Deep|Bayes & PRAIRIE AI ML summer schools. 2019
5G & Beyond Graduate Support Program and Bilkent Graduate Scholarship 2018 - 2020
Research Excellence Award Awarded by Bilkent University. 2018

Invited Talks

MIT - FL Reading Group 2021

Professional Activities

President of USC Turkish Graduate Student Association (TGSA) Jun 2022 - Present
Techincal Program Committee Member at the CrossFL Workshop, MLSYS2022 2022
Organizer at the 1st FedGraph2022 Workshop 2022
Teaching Assistant at ProbAI 2021 Summer School 2021


The 1st International Workshop on Federated Learning with Graph Data (FedGraph2022-ACM CIKM)
Workshop on Cross-Community Federated Learning: Algorithms, Systems and Co-designs (CrossFL-MLSYS'22)
Neural Information Processing Systems (NeurIPS'22, Main and Dataset and Benchmark Tracks)
International Conference on Learning Representations (ICLR'21)
International Conference on Machine Learning (ICML'21)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'21)
IEEE Transactions of Neural Networks and Learning Systems (TNNLS)
IEEE Transactions of Big Data (TBD)

Selected Courses

Theory of Machine Learning Dynamics of Representation Learning
Large-Scale Optimization for Machine Learning Privacy in the World of Big Data


FedML-AI/FedML | FedML - A Research-oriented Federated Learning Library 2020
FedML-AI/FedGraphNN | A Research-oriented Federated Learning Library for GNNs 2021
FedML-AI/SpreadGNN | Serverless Multi-Task Federated Learning for GNNs 2021


Languages C, C++, Java, MATLAB, Julia, Python
Frameworks JAX, NumPy, Pandas, PyTorch, Pyro, SciPy, Keras
Tools Linux, vim, git, tmux, zsh

All credit goes to Brandon Amos. Last updated on 2023-04-23