Dr. Long Tan Le’ s research interests span federated learning, data mining, edge AI, and the Internet of Things (IoT). His work focuses on designing robust and efficient distributed learning systems for resource-constrained and heterogeneous edge environments.
He has made notable contributions to federated PCA on Grassmann manifolds for IoT anomaly detection, distributionally robust federated learning for mobile edge networks, and federated deep equilibrium learning for enhanced personalization. His research also addresses practical challenges in security for SDN-enabled networks, real-time edge-based applications such as parking occupancy detection, and hardware acceleration using FPGA for intrusion detection systems.
His publications appear in leading venues such as IEEE/ACM Transactions on Networking, IEEE INFOCOM, and Mobile Networks and Applications, and his collaborations extend across academia and industry to bring theoretical advances into real-world deployment.