About Me
I am a Final Year Ph.D. candidate in the School of Electrical Engineering at the Korea Advanced Institute of Science and Technology (KAIST), South Korea. Advised by Prof. Jaekyun Moon , my research bridges Active Learning and Distributed Machine Learning. I am also interested in assisting others on their path in the world of Machine Learning and academia.
Beyond the lab, I am passionate about community leadership and mentorship. I have served as the Vice President of the Pakistan Student Association (PSA) at KAIST and as an International Student Mentor at universities.
When I am not working on my dissertation, you can usually find me sharing my life experiences, hitting the slopes to snowboard, or practicing new languages.
📰 News
- March 2026 – Our Workshop, “AI Modeling for Disappearing Knowledge (AIM4DK)”, has been accepted in IJCAI-ECAI’26.
- Feb 2026 – Successfully passed my Ph.D. Dissertation Proposal Defense!
- Feb 2026 – Our paper, “PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion”, has been featured in TMLR’26.
- Oct 2024 – Our paper, “Pruning-based Data Selection and Network Fusion for Efficient Deep Learning”, was accepted to Attributing Model Behavior at Scale Workshop at NeurIPS’24.
- Oct 2023 – Our paper, “EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning”, was accepted to NeurIPS’23.
- Feb 2023: – Our paper, “Distribution Aware Active Learning via Gaussian Mixtures”, was accepted to Pitfalls of limited data and computation for Trustworthy ML Workshop at ICLR’23.
- March 2022 – Joined MoonLab @ KAIST as a Ph.D. Student.
- Dec 2021 – Successfully passed my Master’s Dissertation Defense!
📚 Publications
Humaira Kousar, HI Bhatti, J Moon, “Pruning-based Data Selection and Network Fusion for Efficient Deep Learning”. Neural Information Processing Systems (NeurIPS), Workshop on Attributing Model Behavior at Scale, 2024 Pdf
Humaira Kousar, HI Bhatti, J Moon, “PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion”. Transactions on Machine Learning Research (TMLR), 2026, (Featured Certification). Pdf
“Communication-Efficient Federated Learning via Model-Agnostic Projection Adaptation”.(under review)
MM Rahimi, HI Bhatti, Y Park, Humaira Kousar, J Moon. “EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning.” Advances in Neural Information Processing Systems(NeurIPS), 2024. Pdf
Y Park, DJ Han, J Park, W Choi, Humaira Kousar, J Moon. “Distribution Aware Active Learning via Gaussian Mixtures”. International Conference on Learning Representations (ICLR), Workshop on Pitfalls of limited data and computation for Trustworthy ML,2023. Pdf
Humaira Kousar, M Atif, H Ali, MH Kundi. “WHEGSTR: A Multiterrain Robot with C-Shaped Whegs, Implementation of Error Minimization Technique and using Artificial Neural Network (ANN)”. 2019 International Conference on Green and Human Information Technology (ICGHIT). IEEE, 2019.
📚 Patent
Device and Method for Distribution Aware Active Learning using Gaussian Mixture. Younghyun Park, Jungwuk Park, Dong-jun Han, Wonjeong Choi, Humaira Kousar and Jaekyun Moon. Application Number: KR 10-2024-0035374, Application Date: Mar 13, 2024
📚Research Projects
Active Learning Algorithms for Efficient Utilization of Unlabeled Defense Data. Center for Applied Research in Artificial Intelligence (CARAI), Funded by Agency for Defense Development (ADD); (2021 – Present)
📚 Accademic Service
- Organizer – IJCAI Workshop, AIM4DK: AI Modeling for Disappearing Knowledge. Workshop at IJCAI-ECAI’26.
- Reviewer – ICLR, International Conference on Learning Representations, 2026
- Reviewer – AAAI, Conference on Artificial Intelligence, 2026
- Reviewer – WiML, Advances in Neural Information Processing Systems (NeurIPS), 2025
- Volunteer – WiML, Advances in Neural Information Processing Systems (NeurIPS), 2025
- Reviewer – ATTRIB, Advances in Neural Information Processing Systems (NeurIPS), 2024