M. Hadi Amini

About

M. Hadi Amini is a prominent researcher at the intersection of federated learning, distributed machine learning, and resource-constrained computing systems, with a particular focus on Internet-of-Things (IoT) environments and edge intelligence. His work addresses one of the most pressing challenges in modern AI deployment: enabling robust machine learning in privacy-sensitive, resource-limited settings without centralizing sensitive user data. Amini's most influential contribution, a comprehensive survey on federated learning for resource-constrained IoT devices, has garnered an impressive 719 citations since its 2021 publication, establishing it as a foundational reference in the field. This work systematically examines how federated learning enables decentralized, on-device training while preserving data privacy — a critical consideration as connected devices proliferate globally. His subsequent research extends these principles into practical domains, including human activity recognition and autonomous mobile robotics through projects like FedAR, demonstrating his commitment to bridging theoretical frameworks with real-world applications. Across his body of work, Amini consistently tackles the tension between computational efficiency, privacy preservation, and model performance — making his research especially valuable to engineers, data scientists, and policymakers navigating the rapidly evolving landscape of distributed AI systems.

Research Focus

Key Achievements

Top Papers

1. 1
   A Survey on Federated Learning for Resource-Constrained IoT Devices

   719 citations · 2021
2. 2
   Exploiting Federated Learning Technique to Recognize Human Activities in Resource-Constrained Environment

   4 citations · 2022
3. 3
   FedAR: Activity and Resource-Aware Federated Learning Model for Distributed Mobile Robots

   2 citations · 2020

Key Collaborators

Contact & Links