Ideas, methods, and systems.

2026

1. CVPR

   Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression

   Minh-Duong Nguyen, Senura Wanasekara, Le-Tuan Nguyen, and 4 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2026

   Abs arXiv HTML PDF

   Federated On-server Unlearning (FOUL) removes client data contributions through a communication-efficient learning-to-unlearn stage and on-server knowledge aggregation, reducing computation, communication, and time-to-forget.

2025

1. arXiv

   Distributionally Robust Wireless Semantic Communication with Large AI Models

   Long Tan Le, Senura Hansaja Wanasekara, Zerun Niu, and 7 more authors

   2025

   Abs DOI HTML

   A distributionally robust approach for wireless semantic communication with large AI models that addresses uncertainty in wireless channels and semantic information transmission.

2. arXiv

   GoodSpeed: Optimizing Fair Goodput with Adaptive Speculative Decoding in Distributed Edge Inference

   Phuong Tran, Tzu-Hao Liu, Long Tan Le, and 6 more authors

   2025

   Accepted at INFOCOM 2026

   Abs DOI HTML

   A distributed speculative decoding framework for multi-server edge inference that optimizes goodput while ensuring proportional fairness.

2024

1. MONET

   Distributionally Robust Federated Learning for Mobile Edge Networks

   Long Tan Le, Tung-Anh Nguyen, Tuan-Dung Nguyen, and 5 more authors

   Mobile Networks and Applications, 2024

   Abs DOI HTML

   A distributionally robust federated learning framework for mobile edge networks under data heterogeneity and distribution shifts.

2. arXiv

   Federated PCA on Grassmann Manifold for IoT Anomaly Detection

   Tung-Anh Nguyen, Long Tan Le, Tuan Dung Nguyen, and 4 more authors

   2024

   Abs HTML

   A federated learning framework for large-scale multivariate time-series anomaly detection.

3. arXiv

   Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization

   Long Tan Le, Tuan Dung Nguyen, Tung-Anh Nguyen, and 4 more authors

   2024

   Abs HTML

   A federated deep equilibrium learning approach for personalization through compact global representations.

4. arXiv

   iREPO: Implicit Reward Pairwise Difference based Empirical Preference Optimization

   Long Tan Le, Han Shu, Tung-Anh Nguyen, and 2 more authors

   2024

   Abs HTML

   An empirical preference optimization framework for aligning large language models with human expectations.

2023

1. TNNLS

   A New Look and Convergence Rate of Federated Multitask Learning With Laplacian Regularization

   Canh T. Dinh, Tung T. Vu, Nguyen H. Tran, and 2 more authors

   IEEE Transactions on Neural Networks and Learning Systems, 2023

   Abs DOI HTML Code

   A federated multitask learning framework using Laplacian regularization with FedU and dFedU algorithms.

2. INFOCOM

   Federated PCA on Grassmann Manifold for Anomaly Detection in IoT Networks

   Tung-Anh Nguyen, Jiayu He, Long Tan Le, and 2 more authors

   In IEEE INFOCOM, 2023

   Abs DOI HTML

   A federated principal component analysis framework on Grassmann manifold for IoT anomaly detection.

2022

1. arXiv

   On the Generalization of Wasserstein Robust Federated Learning

   Tung-Anh Nguyen, Tuan Dung Nguyen, Long Tan Le, and 2 more authors

   2022

   Abs HTML

   A Wasserstein distributionally robust optimization approach for federated learning under non-IID data and distribution shifts.

2020

1. arXiv

   Personalized Federated Learning with Moreau Envelopes

   Canh T. Dinh, Nguyen H. Tran, and Tuan Dung Nguyen

   2020

   Abs HTML Code

   A personalized federated learning algorithm using Moreau envelopes for statistical heterogeneity in federated learning.

2. TON

   Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation

   Canh T. Dinh, Nguyen H. Tran, Minh N. H. Nguyen, and 4 more authors

   IEEE/ACM Transactions on Networking, 2020

   Abs DOI HTML

   A convergence analysis and resource allocation study for federated learning over wireless networks.