Dr. Fekri holds B.Sc. and M.Sc. degrees from Sharif University of Technology and a Ph.D. in Electrical and Computer Engineering from Georgia Tech. After receiving his PhD degree, he joined to the School of ECE at Georgia Tech as an assistant professor, where he is now the John Pippin Chair Professor and the ECE-GTRI Fellow. He is a member of the Center for Signal and Information Processing (CSIP), the Georgia Tech Center for Machine Learning, the Center for Energy and Geo Processing (CeGP).
Prof. Fekri is the founder of the SENTINEL Research Lab that has a multidisciplinary flavor in four intertwined broad areas of 1. Information, 2. Processing/Learning, 3. Communications, and 4. Decision Intelligence. In particular, he applies machine learning and logical reasoning, statistics and information theory to fundamental research problems in semantic communications, reinforcement learning, inductive logic reasoning, neuro-logical reasoning in Language Models, learning in distributed or federated environments, causal discovery, probabilistic modeling, biomarker sensing and molecular communication in biology. In the past, Prof. Fekri investigated the theory and practice of error correction codes, the application of mathematical tools to modern networking, spanning from network packet compression and performance characterization of wired/wireless networks to the design, analysis, and optimization of communication protocols. He also developed novel frameworks for approximate computing, social computing, and the first cryptographic system using finite field wavelet transforms.
Dr. Fekri serves on the editorial board of the IEEE Transactions on Molecular, Biological, and Multi-Scale Communications, and on both the Executive and Technical Program Committees of several IEEE as well as Machine Learning conferences. In the past, he served on the editorial board of IEEE Transactions on Communications, and the Elsevier Journal on PHYCOM.
- Machine Learning
- Information Theory
- Semantic Communication for Artificial Intelligence
- Learning via Logical Reasoning
- Reinforcement Learning
- Large Language Models
- Causal Discovery and Biomarker Sensing
- Molecular Communication in Biology
- ECE-GTRI Fellow, Spring 2020.
- Sony Faculty Research Innovation Award, 2018.
- IEEE Fellow, 2015.
- Class of 1934 Course Survey Teaching Effectiveness Award from the Georgia Tech Center for the Enhancement of Teaching and Learning, 2012, 2015.
- Outstanding Junior Faculty Member Award from School of Electrical and Computer Engineering, Georgia Institute of Technology, 2006.
- Southeastern Center for Electrical Engineering Education (SCEEE) Young Faculty Development Award, 2003.
- National Science Foundation Career Award, 2001.
- Sigma Xi Best Ph.D. Thesis Award of the Georgia Institute of Technology, 2000.
- Hang Zhang, Afshin Abdi, and Faramarz Fekri, "A General Compressive Sensing Construct using Density Evolution," IEEE Transactions on Signal Processing (TSP), accepted in Nov. 2022, to appear in 2023.
- Sethuraman, Muralikrishnna G., Romain Lopez, Rahul Mohan, Faramarz Fekri, Tommaso Biancalani, and Jan-Christian Hütter, "NODAGS-Flow: Nonlinear Cyclic Causal Structure Learning." In The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2023.
- Ahmet Faruk Saz, Yashas Malur Saidutta, Mustafa Akdeniz, Nageen Himayat, Faramarz Fekri, “Attri-Sense: An Attribute-based Privacy Framework for Federated Learning,” IEEE SPAWC, Shanghai, China, Fall 2023.
- Siheng Xiong, Yuan Yang, Faramarz Fekri, and James Clayton Kerce, "TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs," In International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023.
- Afshin Abdi, Saeed Rashidi, Faramarz Fekri, Tushar Krishna,” Efficient Distributed Inference of Deep Neural Networks via Restructuring and Pruning,” Thirty-Seventh AAAI Conference on Artificial Intelligence, Washington DC, USA, Feb. 2023.
- Yuan Yang, Faramarz Fekri, J. Clayton Kerce, Ali Payani, "LogicDP: Creating Labels for Graph Data via Inductive Logic Programming" International Conference on Machine Learning (ICLR), Kigali, Rwanda, May 2023.
- Sethuraman, Muralikrishnna G., Hang Zhang, and Faramarz Fekri. “Design of Compressed Sensing System via Density Evolution Framework for Structure Recovery in Graphical Models.” Allerton Conference, Oct. 2023.
- D. Xu, and F. Fekri, "Improving actor-critic reinforcement learning via Hamiltonian Monte Carlo Method," IEEE Transactions on Artificial Intelligence, pp. 1-12, Oct. 2022.
- Y. Yang, J. Clayton Kerce, and F. Fekri, "LogicDef: An Interpretable Defense Framework Against Adversarial Examples via Inductive Scene Graph Reasoning," Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022.
- Y. M. Saidutta, F. Fekri, A. Abdi, “A Machine Learning Framework for Privacy-Aware Distributed Functional Compression over AWGN Channels,” In 2022 IEEE Information Theory Workshop (ITW) (pp. 380-385) at Mumbai, India. Nov. 2022.
- D. Xu, F. Fekri, “Integrating Symbolic Planning and Reinforcement Learning for Following Temporal Logic Specifications,” International Joint Conference on Neural Networks (IJCNN), 2022.
- Y. M. Saidutta, A. Abdi, and F. Fekri, “Joint Source-Channel Coding over Additive Noise Analog Channels using Mixture of Variational Autoencoders.” IEEE Journal of Selected Areas in Comm. Series on Machine Learning in Communications and Networks, vol. 39, no. 7, pp. 2000-2013, doi: 10.1109/JSAC.2021.3078489, July, 2021.
- Ahmad Beirami, Faramarz Fekri, “Network Traffic Compression with Side Information,” IEEE Access, 8, pp.90023-90034, May 2020.