Výsledky vyhledávání - "Nguyễn Thế Thao"

Report

FedCert: Federated Accuracy Certification

Autor: Nguyen, Minh Hieu, Nguyen, Huu Tien, Nguyen, Trung Thanh, Nguyen, Manh Duong, Hoang, Trong Nghia, Nguyen, Truong Thao, Nguyen, Phi Le

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against data pertu

Externí odkaz: http://arxiv.org/abs/2410.03067

Zobrazit plný text záznamu

Report

Fuzzy Q-Learning-Based Opportunistic Communication for MEC-Enhanced Vehicular Crowdsensing

Autor: Nguyen, Trung Thanh, Nguyen, Truong Thao, Nguyen, Thanh Hung, Nguyen, Phi Le

This study focuses on MEC-enhanced, vehicle-based crowdsensing systems that rely on devices installed on automobiles. We investigate an opportunistic communication paradigm in which devices can transmit measured data directly to a crowdsensing server

Externí odkaz: http://arxiv.org/abs/2405.01057

Zobrazit plný text záznamu

Report

Q-learning-based Opportunistic Communication for Real-time Mobile Air Quality Monitoring Systems

Autor: Nguyen, Trung Thanh, Nguyen, Truong Thao, Nguyen, Dinh Tuan Anh, Nguyen, Thanh Hung, Nguyen, Phi Le

We focus on real-time air quality monitoring systems that rely on devices installed on automobiles in this research. We investigate an opportunistic communication model in which devices can send the measured data directly to the air quality server th

Externí odkaz: http://arxiv.org/abs/2405.01609

Zobrazit plný text záznamu

Report

KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training

Autor: Nguyen, Truong Thao, Gerofi, Balazs, Martinez-Noriega, Edgar Josafat, Trahay, François, Wahib, Mohamed

This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training. Using information about the loss and prediction confidence during training,

Externí odkaz: http://arxiv.org/abs/2310.10102

Zobrazit plný text záznamu

Report

FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection

Autor: Nguyen, Thuy Dung, Nguyen, Anh Duy, Wong, Kok-Seng, Pham, Huy Hieu, Nguyen, Thanh Hung, Nguyen, Phi Le, Nguyen, Truong Thao

Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. The decentralized nature of FL makes it susceptible to adversarial attacks, especially backdoor insertion during training. Recently, the edge-case

Externí odkaz: http://arxiv.org/abs/2305.00328

Zobrazit plný text záznamu

Report

CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization

Autor: Nguyen, Nang Hung, Nguyen, Duc Long, Nguyen, Trong Bang, Nguyen, Thanh-Hung, Pham, Huy Hieu, Nguyen, Truong Thao, Nguyen, Phi Le

Federated learning enables edge devices to train a global model collaboratively without exposing their data. Despite achieving outstanding advantages in computing efficiency and privacy protection, federated learning faces a significant challenge whe

Externí odkaz: http://arxiv.org/abs/2302.10413

Zobrazit plný text záznamu

Report

FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training

Autor: Nguyen, Quan, Pham, Hieu H., Wong, Kok-Seng, Nguyen, Phi Le, Nguyen, Truong Thao, Do, Minh N.

We introduce FedDCT, a novel distributed learning paradigm that enables the usage of large, high-performance CNNs on resource-limited edge devices. As opposed to traditional FL approaches, which require each client to train the full-size neural netwo

Externí odkaz: http://arxiv.org/abs/2211.10948

Zobrazit plný text záznamu

Report

FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning

Autor: Nguyen, Nang Hung, Nguyen, Phi Le, Nguyen, Duc Long, Nguyen, Trung Thanh, Nguyen, Thuy Dung, Pham, Huy Hieu, Nguyen, Truong Thao

The uneven distribution of local data across different edge devices (clients) results in slow model training and accuracy reduction in federated learning. Naive federated learning (FL) strategy and most alternative solutions attempted to achieve more

Externí odkaz: http://arxiv.org/abs/2208.02442

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání