Scholar
Matin Mortaheb
Google Scholar ID: M1WS-AYAAAAJ
Ph.D. Student at the Department of Electrical Engineering, University of Maryland
Citations & Impact
Citations
90
H-index
6
i10-index
3
Publications
19
Co-authors
2
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Semantic Multi-Resolution Communications' accepted to IEEE Global Communications Conference; 'Personalized decentralized multi-task learning over dynamic communication graph' presented at the IEEE Conference on Information Sciences and Systems; 'Hierarchical over-the-air FedGradNorm' included in the 56th Asilomar Conference on Signals, Systems, and Computers; 'FedGradNorm: personalized federated gradient-normalized multi-task learning' featured in the EEE International Workshop on Signal Processing Advances in Wireless Communications.
Research Experience
- Involved in deep learning-based video streaming projects aimed at improving live video quality over wireless networks through real-time adjustment of encoder parameters; also conducted research on semantic multi-resolution communications, developing a novel deep learning multi-resolution joint source-channel coding framework.
Education
- 5th year Ph.D. candidate in the Electrical and Computer Engineering Department at the University of Maryland, under the supervision of Prof. Sennur Ulukus.
Background
- Research interests include wireless communication, federated learning, multi-task learning, semantic communication, and video streaming technologies. Currently working on personalization, statistical heterogeneity (non-I.I.D), and communication efficiency in federated learning; also focusing on end-to-end semantic communication, semantic multi-user communication, and semantic multi-resolution communication.
