Research

Our research focuses on cutting-edge areas in artificial intelligence, machine learning, and distributed systems. We investigate novel approaches to improve AI efficiency, fairness, and interpretability, with particular emphasis on large language models, federated learning, and edge computing.

Our team explores both theoretical foundations and practical applications, contributing to the advancement of intelligent systems that can operate effectively in real-world, resource-constrained environments.

Highlighted

Distributionally Robust Wireless Semantic Communication with Large AI Models

Long Tan Le, Senura Hansaja Wanasekara, Zerun Niu, Yansong Shi, Nguyen H. Tran, …, Walid Saad, Dusit Niyato, Zhu Han, Choong Seon Hong, H. Vincent Poor

arXiv · 01 Jan 2024 · doi:10.48550/ARXIV.2506.03167

A distributionally robust approach for wireless semantic communication with large AI models that addresses uncertainty in wireless channels and semantic information transmission, enhancing reliability in AI-powered communication systems.

ArXiv

All

2024

Lossy Compression of Multi-Channel EEG and PPG Signals Based on Golomb-Rice Coding with Parameter Estimation

Senura Hansaja Wanasekara, Han Huy Dung, Ngoc Hung Nguyen, Van-Dinh Nguyen

2024 International Conference on Advanced Technologies for Communications (ATC) · 17 Oct 2024 · doi:10.1109/atc63255.2024.10908307

Federated PCA on Grassmann Manifold for IoT Anomaly Detection

Tung-Anh Nguyen, Long Tan Le, Tuan Dung Nguyen, Wei Bao, Suranga Seneviratne, Choong Seon Hong, Nguyen H. Tran

arXiv · 10 Jul 2024 · arxiv:2407.07421

A federated learning framework combining Koopman operator theory and reservoir computing for large-scale multivariate time-series anomaly detection. The method leverages dynamic system modeling to detect anomalies in distributed time-series data while preserving privacy.

ArXiv

federated-learning koopman-operator reservoir-computing time-series-analysis anomaly-detection multivariate-data privacy-preserving

$i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization

Long Tan Le, Han Shu, Tung-Anh Nguyen, Choong Seon Hong, Nguyen H. Tran

arXiv · 24 May 2024 · arxiv:2405.15230

iREPO introduces an implicit reward pairwise difference based empirical preference optimization framework for aligning large language models with human expectations. The method uses regression on preference pairs to optimize model alignment more effectively.

ArXiv

preference-optimization large-language-models human-alignment empirical-optimization reward-modeling llm-alignment

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

Long Tan Le, Tuan Dung Nguyen, Tung-Anh Nguyen, Choong Seon Hong, Suranga Seneviratne, Wei Bao, Nguyen H. Tran

arXiv · 22 May 2024 · arxiv:2309.15659

A federated deep equilibrium learning approach that harnesses compact global representations to enhance personalization in federated settings. The method addresses the trade-off between personalization and global knowledge sharing through equilibrium point modeling.

ArXiv

federated-learning deep-equilibrium-learning personalization global-representations equilibrium-modeling knowledge-sharing

Distributionally Robust Federated Learning for Mobile Edge Networks

Long Tan Le, Tung-Anh Nguyen, Tuan-Dung Nguyen, Nguyen H. Tran, Nguyen Binh Truong, Phuong L. Vo, Bui Thanh Hung, Tuan Anh Le

Mobile Networks and Applications · 01 Jan 2024 · doi:10.1007/s11036-024-02316-w

A distributionally robust federated learning framework designed for mobile edge networks that addresses data heterogeneity and distribution shifts in edge computing environments. The method enhances robustness and generalization capabilities in resource-constrained mobile edge settings.

Springer

federated-learning mobile-edge-computing distributionally-robust-optimization edge-networks robustness heterogeneity

Distributionally Robust Wireless Semantic Communication with Large AI Models

Long Tan Le, Senura Hansaja Wanasekara, Zerun Niu, Yansong Shi, Nguyen H. Tran, …, Walid Saad, Dusit Niyato, Zhu Han, Choong Seon Hong, H. Vincent Poor

arXiv · 01 Jan 2024 · doi:10.48550/ARXIV.2506.03167

ArXiv

semantic-communication large-ai-models distributionally-robust-optimization wireless-communication uncertainty robustness

2023

Federated PCA on Grassmann Manifold for Anomaly Detection in IoT Networks

Tung-Anh Nguyen, Jiayu He, Long Tan Le, Wei Bao, Nguyen H. Tran

arXiv · 01 Jan 2023 · arxiv:2212.12121

A federated principal component analysis (PCA) framework on Grassmann manifold for IoT anomaly detection. The method uses privacy-preserving federated learning to aggregate normal network behavior features across IoT devices, with ADMM-based gradient learning on Grassmann manifolds for fast training and low detection latency.

ArXiv

IEEE INFOCOM

federated-learning pca grassmann-manifold iot anomaly-detection privacy-preserving admm

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

Canh T. Dinh, Tung T. Vu, Nguyen H. Tran, Minh N. Dao, Hongyu Zhang

IEEE Transactions on Neural Networks and Learning Systems · 01 Jan 2023 · doi:10.1109/TNNLS.2022.3224252

A novel federated multi-task learning framework using Laplacian regularization that unifies conventional federated learning, personalized federated learning, and federated multi-task learning. Proposes FedU and dFedU algorithms with proven convergence rates.

ArXiv

IEEE Xplore

Code Repository

federated-multi-task-learning laplacian-regularization personalized-federated-learning convergence-analysis distributed-systems machine-learning

2022

On the Generalization of Wasserstein Robust Federated Learning

Tung-Anh Nguyen, Tuan Dung Nguyen, Long Tan Le, Canh T. Dinh, Nguyen H. Tran

arXiv · 02 Jun 2022 · arxiv:2206.01432

A Wasserstein distributionally robust optimization approach (WAFL) for federated learning that addresses non-i.i.d. data distribution problems. The method reformulates robust federated learning as empirical surrogate risk minimization with convergence guarantees, showing better generalization than FedAvg under distribution shifts.

ArXiv

federated-learning wasserstein-distance distributionally-robust-optimization non-iid-data generalization robustness

2020

Personalized Federated Learning with Moreau Envelopes

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

arXiv · 16 Jun 2020 · arxiv:2006.08848

A novel personalized federated learning algorithm using Moreau envelopes that addresses statistical heterogeneity in federated learning by enabling each client to learn a personalized model while benefiting from the global knowledge.

ArXiv

Code Repository

personalized-federated-learning moreau-envelopes statistical-heterogeneity machine-learning distributed-systems

2019

Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation

Canh T. Dinh, Nguyen H. Tran, Minh N. H. Nguyen, Choong Seon Hong, Wei Bao, Albert Y. Zomaya, Vincent Gramoli

arXiv · 29 Oct 2019 · arxiv:1910.13067

A comprehensive study of federated learning over wireless networks, providing convergence analysis and resource allocation optimization for mobile user equipments with heterogeneous data and physical resources.

ArXiv

IEEE Xplore

federated-learning wireless-networks convergence-analysis resource-allocation mobile-computing distributed-systems