Nguyen Huu Nhat Minh

Nguyen Huu Nhat Minh

I received Ph.D. degree in Computer Science and Engineering from Kyung Hee University, South Korea, in 2020. He continued PostDoc with Federated Learning and Democratized Learning at Intelligent Networking lab, Kyung Hee University, South Korea. He is Deputy Head of Department of Science, Technology, and International Cooperation, and In charge of Research Program at Digital Science and Technology Institute, The University of Danang – Vietnam - Korea University of Information and Communication Technology, Vietnam. He received the best KHU Ph.D. thesis award in engineering in 2020. He had publications in premier ACM/IEEE journals and conferences. His research interests include wireless communications, federated learning, NLP, and computer vision.

About me

Currently, I am working as

  • Deputy Head of Department of Science, Technology, and International Cooperation
  • In charge of Research Program at Digital Science and Technology Institute (eSTI), VKU, Vietnam
  • Leading Research team of Intelligent Systems in eSTI
  • A collaborator with multiple research groups:
    • Networking Intelligence Lab, Kyung Hee University, Korea (Multimodal Federated Learning)
    • SPACHES lab at University of South Florida, USA (Medical Imaging Research)

Email: nhnminh@vku.udn.vn, nhatminhhcmut@gmail.com, minhnhn@khu.ac.kr

This is my Google Scholar link and DBLP link

Personal Statement

As a research scientist, I am passionate about developing sustainable intelligent solutions for open challenges in future multi-modal, multi-domain complex systems. Throughout this journey, I keep challenging myself with an open mind and exploring many new domains to broaden my limited understanding.

I am currently working on the following research topics:

1. Multimodal Learning, Natural Language Processing, and Speech Recognition

Working towards recent hot topics such as

  • DaNang NLP Toolkits: Vietnamese NLP & Speech Recognition
  • Generative, Computer Vision Applications
  • Compressive Multimodal Representation toward Personalized AI

2. Federated Learning

I collaborate with Networking Intelligence lab on several Federated Learning papers that were published on (INFOCOM 2019) and other published papers in a high-quality journal such as:

  • My paper about Federated Learning with the title “Toward Multiple Federated Learning Services Resource Sharing in Mobile Edge Networks” was published to IEEE Transactions on Mobile Computing
  • The ACM/IEEE Transactions on Networking journal version of INFOCOM paper “Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation” was published in IEEE/ACM Transactions on Networking. ArXiv
  • I am also the co-author of the published Federated Learning papers in IEEE Transactions on Wireless Communications, IEEE Communications Magazine, and Elsevier Neural Networks.

3. Distributed and Democratized Learning

I and my team are enthusiastic about the future of personalized services using distributed AI platforms. The complex hierarchical social structure inspires us to move toward a novel distributed learning paradigm, namely Democratized Learning (Dem-AI). We envision Dem-AI to play an important role in this journey and step by step bring Dem-AI systems from the philosophy to the practical implementation. Through our studies, we aim to profoundly analyze and better control the vital generalization and specialization capability of the learning models in the Dem-AI systems.

  • Our first paper about Dem-AI philosophy was accepted in IEEE Computational Intelligence Magazine. ArXiv
  • We have recently published our initial implementation (ie., DemLearn algorithm) of Dem-AI in IEEE Transactions on Neural Networks and Learning Systems ArXiv. The code is available on Github.
  • Dem-AI works were presented in an invited talk at The International Workshop on Distributed Cloud Computing (DCC) co-located with ACM SIGMETRICS 2020. Link
  • The third paper with the title “Edge-assisted Democratized Learning Towards Federated Analytics” was published in IEEE Internet of Things Journal in 2021.

4. Colocation Base Stations and Edge Computing and Wireless Sensor Networks

I studied the resource-sharing model for colocation services such as colocation Mobile Base Stations and edge computing during my Ph.D. thesis. Accordingly, we published a proposal for the Fair Sharing of Backup Power on IEEE Transactions on Wireless Communications (IEEE TWC) and another proposal for Colocation Edge Computing on IEEE Transactions on Vehicular Technology (IEEE TVT).