About Me
I am a PhD candidate at KAIST, working in the Moon Lab under the supervision of Prof. Jaekyun Moon. My research focuses on Federated Learning, Local Error Learning, Split Learning and Active Learning. My long-term goal is to develop scalable and efficient learning paradigms for distributed neural networks to address heterogenity issues in large-scale systems.
Before joining KAIST, I earned my Bachelor’s degree in Electrical Engineering with a minor in Computer Science from the University of Engineering and Technology (UET), Lahore, where I was fortunate to work under the guidance of Dr. Muhammad Tahir.
News
- [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 2024.
- [Oct. 2023] Our paper, “EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning,” was accepted to NeurIPS 2023.
- [July 2022] Presented “Locally Supervised Learning with Periodic Global Guidance” at the ICML Workshop on Hardware Aware Efficient Training.
- [Dec. 2021] Successfully defended my Master’s thesis.
- [July 2021] Presented “Accelerating Federated Learning with Split Learning on Locally Generated Losses” at the FL-ICML21 poster session.
Publications
-
NeurIPS
Humaira Kousar*, Hasnain Irshad Bhatti*, Jaekyun Moon
Neural Information Processing Systems (NeurIPS), 2024, Workshop on Attributing Model Behavior at Scale.
-
NeurIPS
Mohammad Mahdi Rahimi, Hasnain Irshad Bhatti, Younghyun Park, Humaira Kousar, Do-Yeon Kim, Jaekyun Moon
Advances in Neural Information Processing Systems (NeurIPS), 2023.
-
ICML
Hasnain Irshad Bhatti, Jaekyun Moon
ICML 2022 Hardware Aware Efficient Training (HAET) Workshop, 2022.
-
IC2S2
Wenchao Dong, Bryan Wong, Hasnain Irshad Bhatti, Lanu Kim, Meeyoung Cha
International Conference on Computational Social Science (IC2S2), 2022 and Korea Computer Congress 2022.
-
ICML
Dong-Jun Han, Hasnain Irshad Bhatti, Jungmoon Lee, Jaekyun Moon
ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality, 2021.
Services
Conference Reviewers
Powered by Jekyll and Minimal Light theme.