activity
20202024
most citedFedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training

12 citations · 30 across the 5 of their papers we have counts for

collaborators

5 papers

cs.NI2024★ 6 cited

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

Trung Thanh Nguyen, Truong Thao Nguyen, Dinh Tuan Anh Nguyen +2

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 de…

cs.CV2023

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

Thuy Dung Nguyen, Anh Duy Nguyen, Kok-Seng Wong +4

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, e…

cs.CV2022★ 12 cited

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

Quan Nguyen, Hieu H. Pham, Kok-Seng Wong +3

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 app…

cs.DC2021★ 11 cited

An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks

Albert Njoroge Kahira, Truong Thao Nguyen, Leonardo Bautista Gomez +3

Deep Neural Network (DNN) frameworks use distributed training to enable faster time to convergence and alleviate memory capacity limitations when training large models and/or using…

cs.DC2020★ 1 cited

Scaling Distributed Deep Learning Workloads beyond the Memory Capacity with KARMA

Mohamed Wahib, Haoyu Zhang, Truong Thao Nguyen +5

The dedicated memory of hardware accelerators can be insufficient to store all weights and/or intermediate states of large deep learning models. Although model parallelism is a via…