Overview
Bing Luo is an Assistant Professor of Data and Computational Science at Duke Kunshan University (DKU). He also serves as an Honorary Assistant Professor at the University of Hong Kong. Prior to joining DKU, he was a joint Postdoc Researcher at The Chinese University of Hong Kong (Shenzhen) and Yale University. He received his Ph.D. from The University of Melbourne, where he was awarded both the Kenneth Myers Memorial Scholarship (granted to one recipient every two years) and the Robert Bage Memorial Scholarship. Prior to his academic career, he gained several years of industry experience as a Project Manager at China Mobile Corporation Headquarters. He was awarded the Clare Hall Visiting Fellowship at the University of Cambridge, supporting his pre-tenure sabbatical in Fall 2026.
His research focuses on the theory and practice of federated and edge learning, as well as LLM-based agentic systems. His work has been published in leading journals and conferences including IEEE JSAC, TCOM, TMC, INFOCOM, ICDCS, and ACM MobiHoc. His team has developed and open-sourced FedKit, the world’s first cross-platform on-device federated learning framework for both Android and iOS, which has been deployed in FedCampus, DKU’s privacy-preserving health data platform. His group also developed and launched ChatDKU (chatdku.dukekunshan.edu.cn), a RAG-agent AI chatbot designed for the DKU community. He is a senior member of the IEEE. For more information, please visit his webpage: https://luobing1008.github.io/
Current Appointments & Affiliations
Assistant Professor of Data and Computational Science at Duke Kunshan University
·
2022 - Present
DKU Faculty
Recent Publications
An Incentive Mechanism for Federated Learning With Time-Varying Client Availability
Journal Article IEEE Transactions on Mobile Computing · January 1, 2026 In federated learning (FL), distributed users collaboratively train a neural network model under the coordination of a central server. However, time-varying client availability, coupled with non-independent and non-identically distributed (non-IID) dataset ... Full text CiteBeyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives
Conference Mobihoc 2025 Proceedings of the 2025 International Symposium on Theory Algorithmic Foundations and Protocol Design for Mobile Networks and Mobile Computing · October 23, 2025 Federated Unlearning (FU) enables the removal of specific clients' data influence from trained models. However, in non-IID settings, removing clients creates critical side effects: remaining clients with similar data distributions suffer disproportionate p ... Full text CitePriFairFed: A Local Differentially Private Federated Learning Algorithm for Client-Level Fairness
Journal Article IEEE Transactions on Mobile Computing · January 1, 2025 Local Differential Privacy (LDP) is a mechanism used to protect training privacy in Federated Learning (FL) systems, typically by introducing noise to data and local models. However, in real-world distributed edge systems, the non-independent and identical ... Full text CiteEducation, Training & Certifications
University of Melbourne (Australia) ·
2020
Ph.D.