Huong Nguyen

Huong Nguyen

Auto-generated profile, based on publicly available information

Huong Nguyen

University of Oulu

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2024 in Journal of Network and Computer Applications
Verified
Journal Article
Open access
TNTri Nguyen
Tri Nguyen
HNHuong Nguyen
Huong Nguyen
TGTuan Nguyen Gia
Tuan Nguyen Gia

12 August 2023 in Future Generation Computer Systems
Verified
Journal Article
Open access
TNTri Nguyen
Tri Nguyen
HNHuong Nguyen
Huong Nguyen
JPJuha Partala
Juha Partala
Susanna PirttikangasSusanna Pirttikangas
Susanna Pirttikangas



12 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
HNHuong Nguyen
Huong Nguyen
HNHong-Tri Nguyen
Hong-Tri Nguyen
Praveen Kumar DontaPraveen Kumar Donta
Praveen Kumar Donta
Susanna PirttikangasSusanna Pirttikangas
Susanna Pirttikangas
Lauri LovénLauri Lovén
Lauri Lovén
Federated learning has emerged as a privacy-preserving technique for collaborative model training across heterogeneously distributed silos. Yet, its reliance on a single central server introduces potential bottlenecks and risks of single-point failure. Decentralizing the server, often referred to as decentralized learning, addresses this problem by distributing the server role across nodes within the network. One drawback regarding this pure decentralization is it introduces communication inefficiencies, which arise from increased message exchanges in large-scale setups. However, existing proposed solutions often fail to simulate the real-world distributed and decentralized environment in their experiments, leading to unreliable performance evaluations and limited applicability in practice. Recognizing the lack from prior works, this work investigates the correlation between model size and network latency, a critical factor in optimizing decentralized learning communication. We propose a graph-based gossiping mechanism, where specifically, minimum spanning tree and graph coloring are used to optimize network structure and scheduling for efficient communication across various network topologies and message capacities. Our approach configures and manages subnetworks on real physical routers and devices and closely models real-world distributed setups. Experimental results demonstrate that our method significantly improves communication, compatible with different topologies and data sizes, reducing bandwidth and transfer time by up to circa 8 and 4.4 times, respectively, compared to naive flooding broadcasting methods.

1 September 2026 in Neurocomputing
Verified
Journal Article
Open access
HNHuong Nguyen
Huong Nguyen
MBMickaël Bettinelli
Mickaël Bettinelli
AGAmirhossein Ghaffari
Amirhossein Ghaffari
Alexandre BenoitAlexandre Benoit
Alexandre Benoit
HNHong-Tri Nguyen
Hong-Tri Nguyen
Lauri LovénLauri Lovén
Lauri Lovén