Overview
Bing Luo is an Assistant Professor of Data and Computational Science at the Division of Natural and Applied Science at Duke Kunshan University (DKU). Before joining DKU, he served as a Postdoctoral Research Fellow at CUHK(SZ) and Yale University. He received his Ph.D. in Electrical and Electronic Engineering from The University of Melbourne, supported by prestigious scholarships, including the Melbourne Research Scholarship, Robert Bage Memorial Scholarship, and Kenneth Myers Memorial Scholarship.
His research focuses on the theory and practice of federated/distributed machine learning and data analytics, wireless communications and networking, game theory, and optimization, with demo applications in edge-based artificial intelligence (Edge AI), privacy computing, Internet of Things (IoT), and 5G/6G wireless systems. He has published 20 first-author papers in leading journals and conferences, and actively contributes to the academic community by serving as a TPC/PC Member in leading conferences and workshops such as ICDCS, GLOBECOM, ICC, FL-NeurIPS, FL-ICML, FL-IJCAI, and FL-AAAI. More information can be found at: https://luobing1008.github.io/
His research focuses on the theory and practice of federated/distributed machine learning and data analytics, wireless communications and networking, game theory, and optimization, with demo applications in edge-based artificial intelligence (Edge AI), privacy computing, Internet of Things (IoT), and 5G/6G wireless systems. He has published 20 first-author papers in leading journals and conferences, and actively contributes to the academic community by serving as a TPC/PC Member in leading conferences and workshops such as ICDCS, GLOBECOM, ICC, FL-NeurIPS, FL-ICML, FL-IJCAI, and FL-AAAI. More information can be found at: https://luobing1008.github.io/
Current Appointments & Affiliations
Assistant Professor of Data and Computational Science at Duke Kunshan University
·
2022 - Present
DKU Faculty
Recent Publications
PriFairFed: 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 CiteTen Challenging Problems in Federated Foundation Models
Journal Article IEEE Transactions on Knowledge and Data Engineering · January 1, 2025 Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the ... Full text CiteDemo Abstract: Privacy-Preserving Room Occupancy Estimation Using Federated Analytics of BLE Packets
Conference SenSys 2024 - Proceedings of the 2024 ACM Conference on Embedded Networked Sensor Systems · November 4, 2024 We present a privacy-preserving room occupancy estimation method using federated analytics of Bluetooth Low Energy (BLE) packets. By processing data locally and reporting only aggregated device counts, our approach preserves user privacy while achieving 95 ... Full text CiteEducation, Training & Certifications
University of Melbourne (Australia) ·
2020
Ph.D.