News

  • 05/2026: Starting my summer internship at Meta in Seattle, WA, USA.
  • 05/2026: Our paper, Spectral Gap-Driven Coarsening for Dynamic Graph Neural Networks, has been accepted to KDD 2026.
  • 05/2026: Passed my Ph.D. comprehensive exam and am now a Ph.D. candidate!
  • 05/2025: Our paper, TempoBiGen: A Curated Generative Model for Healthcare Mobility Logs with Visit Duration, has been accepted to the ADS track ECML-PKDD 2025.
  • 05/2025: Our paper, Contact Observations from an Intensive Care Unit, has been accepted to Nature Scientific Data Journal.
  • 05/2025: Our paper, Implicit Subgraph Neural Network, has been accepted to ICML 2025.
  • 05/2025: We are in Alexandria, Virginia, USA for SDM 2025!
  • 12/2024: Our paper, Domain Knowledge Augmented Contrastive Learning on Dynamic Hypergraphs for Improved Health Risk Prediction, has been accepted to SDM 2025
  • 05/2024: Our paper, Efficient and Effective Implicit Dynamic Graph Neural Network, has been accepted to KDD 2024.
  • 08/2022: I have started my Ph.D. journey at The University of Iowa.
  • 02/2022: Our paper, Distributionally Robust Fair Principal Components via Geodesic Descents, has been accepted to ICLR 2022.

Biography

I am a Ph.D. candidate in Computer Science at The University of Iowa, advised by Prof. Bijaya Adhikari. I am currently a ML SWE Intern at Meta in Seattle, WA. Prior to joining UIowa, I spent two years as a research resident at VinAI Research and another six months as an AI Engineer there, where I was fortunate to work closely with Prof. Viet Anh Nguyen and Dr. Toan Tran, and many other talented colleagues. I received my Bachelor’s degree in Information Systems from Hanoi University of Science and Technology (HUST), where I worked as an undergraduate research assistant at the Data Science Lab under the mentorship of Prof. Khoat Than.

My research focuses on temporal graph learning for healthcare, addressing two core bottlenecks: the scarcity of high-quality interaction data and the computational scalability of graph learning pipelines. I develop data-centric solutions through two complementary directions: generative models for realistic healthcare interaction data (e.g., mobility logs, patient trajectories), and graph transformation methods that improve both the computational efficiency and representation quality of dynamic graph neural networks. I also have prior experience in active learning, Bayesian neural networks, and distributionally robust optimization. My long-term goal is to build data-efficient and robust graph learning systems that can be reliably deployed in real-world healthcare settings.

Publications

Spectral Gap-Driven Coarsening for Dynamic Graph Neural Networks
Hieu Vu, Rares-Mihail Neagu, Bijaya Adhikari
KDD, 2026 | CODE

TempoBiGen: A Curated Generative Model for Healthcare Mobility Logs with Visit Duration
Hieu Vu, Alberto M Segre, Bijaya Adhikari
ECML-PKDD, 2025 - PDF | SLIDES | CODE

Implicit Subgraph Neural Network
Yongjian Zhong, Liao Zhu, Hieu Vu, Bijaya Adhikari
ICML, 2025 - PDF

Domain Knowledge Augmented Contrastive Learning on Dynamic Hypergraphs for Improved Health Risk Prediction
Akash Choudhuri, Hieu Vu, Kishlay Jha, and Bijaya Adhikari
SDM, 2025 - PDF

Contact Observations from an Intensive Care Unit
Hieu Vu, Roger Struble, Philip M Polgreen, Bijaya Adhikari, Ted Herman
Nature Scientific Data Journal, 2025 - PDF | CODE

Efficient and Effective Implicit Dynamic Graph Neural Network
Yongjian Zhong, Hieu Vu, Tianbao Yang, Bijaya Adhikari
KDD, 2024 - PDF | CODE

Distributionally Robust Fair Principal Components via Geodesic Descents
Hieu Vu*, Toan Tran, Man-Chung Yue, Viet Anh Nguyen
ICLR, 2022 - PDF | SLIDES | CODE

Bayesian Metric Learning for Robust Training of Deep Models under Noisy Labels
Hieu Vu*, Toan Tran, Gustavo Carneiro
preprint, 2020 - PDF

MAP Estimation With Bernoulli Randomness, and Its Application to Text Analysis and Recommender Systems
Xuan Bui, Hieu Vu, Oanh Nguyen, Khoat Than
IEEE Access, 2020 - PDF

Advisors

Collaborators