Hoang-Son Nguyen

About

My current research focuses on generative models that can provably learn a faithful, robust, causal representation of real-world phenomena from high-dimensional data. To achieve this, I use a diverse toolkit from self-supervised learning, signal processing, etc. to develop new methods from first principles. These models will be a trustworthy and reliable backbone supporting applications of AI in scientific discovery, world model for planning, to counterfactual reasoning.

I’m current finishing my M.S. degree at Oregon State University, working with Xiao Fu. Previously, I received my B.Eng. from The Chinese University of Hong Kong in 2024, working with Hoi-To Wai. In the beautiful city of Hong Kong, I studied robust graph learning/graph signal processing against topology perturbation and missing data.

Outside of work, my hobbies are cooking, falling in love with Asian cinema, and photographing my life with close friends whenever I can. Feel free to ping me an email for a coffee chat, work-related or not!

Research Interests

• Deep representation learning: self-supervised learning, compositional generalization, causal representation learning, matrix/tensor factorization, identifiability, multimodal learning
• Graph learning and graph signal processing
• Data-centric AI

News

• [Jan. 2026] Our work on robustness of graph learning algorithms is accepted at ICASSP 2026.
• [Nov. 2025] I’m looking for a PhD starting Fall 2026! My research statement is here.
• [Sep. 2025] Diverse Influence Component Analysis is accepted at NeurIPS 2025!
• [Sep. 2025] A preprint on graph learning is available here, showing that graph topology learning from smooth signals is implicitly robust to missing nodes.
• [April 2025] Our contribution on graph learning under partial observation was accepted at the Graph Signal Processing Workshop 2025. The poster is available here.
• [September 2024] I gave a talk on low-pass graph signal processing at Faculty of Data Science and AI, National Economics University in Hanoi, Vietnam; the slides are here.
• [July 2024] Our work on low-pass graph signal detection under partial observations was awarded Best Student Paper Award at IEEE SAM 2024!

Publications

Selected Awards

• Best Student Paper Award at IEEE SAM, 2024.
• Charles K. Kao Research Exchange Scholarship, 2023.
• CUHK CSE Outstanding Academic Performance, 2021.
• CUHK Admission Scholarship, 2019.

Powered by Jekyll and Minimal Light theme.