Ahmad Faraz Khan

PhD Candidate at Virginia Tech

prof_pic.jpg

Email: ahmadfk@vt.edu

CS@VT

ML Systems Researcher

I am a fourth-year Ph.D. candidate in Computer Science at Virginia Tech in the DSSL lab working with Dr. Ali R. Butt. My research is focused on Machine Learning Systems and Federated Learning.

Currently, I am working on (1) Sys4ML: Enhancing resource utilization, scalability, and efficiency of distributed learning on resource-constrained systems by developing specialized (computing and storage) systems for distributed ML. (2) ML4Sys: (i) Personalized ML: Developing enhanced personalized learning solutions for distributed ML systems. (ii) Incentivized ML: Improving incentive mechanisms within resource-constrained distributed ML systems to ensure fairness and adaptability. (3) LLMs fine-tuning and optimization: Fine-tuning LLMs to reduce sycophancy and prompt optimization for specific tasks. (4) Privacy-aware LLMs: Fine-tuning LLMs with privacy-aware data and utilizing LLMs as human replacements for human in the loop Federated Learning.

I did my B.S. in Computer Science from LUMS University working with Dr. Ihsan Ayyub Qazi and Dr. Zafar Ayyub Qazi.

news

Feb 24, 2024 Serving on the external review committee for ATC 2024.
Feb 07, 2024 Thrilled to announce my paper has been accepted as the first author in EuroSys’24. A big shout-out to my co-authors Azal, Sam, and our team for the collaboration! :sparkles: :smile:
Oct 27, 2023 Excited to share that our paper, with me as the lead author, has been accepted for publication at IEEE BigData’24. Immense gratitude to my co-authors Yuze and Xinran for their invaluable contributions!
Oct 20, 2023 Preprint released for incentivized personalization, now available on Arxiv!
Oct 20, 2023 Paper accepted at IEEE Access, congratulations to Haider and rest of the team!

selected publications

  1. FLOAT: Federated Learning Optimizations with Automated Tuning
    Ahmad Faraz Khan , Azal Ahmad Khan , Ahmed M. Abdelmoniem , and 3 more authors
    In Nineteenth European Conference on Computer Systems (EuroSys ’24) , 2024
  2. Towards cost-effective and resource-aware aggregation at Edge for Federated Learning
    Ahmad Faraz Khan , Yuze Li , Xinran Wang , and 5 more authors
    In 2023 IEEE International Conference on Big Data (BigData) , 2023
  3. A Survey on Attacks and Their Countermeasures in Deep Learning: Applications in Deep Neural Networks, Federated, Transfer, and Deep Reinforcement Learning
    Haider Ali , Dian Chen , Matthew Harrington , and 5 more authors
    IEEE Access, 2023