Research field (2):
Biological, health, and medical informatics
, Mathematical informatics
Research theme for competitive and other funds (2):
2023 - 2026 On Optimal Transport-based Statistical Measures for Graph Structured Data and Applications
2019 - 2020 Advanced machine learning methods for mass spectrometry
Papers (14):
Dai Hai Nguyen, Tetsuya Sakurai. Moreau-Yoshida variational transport: a general framework for solving regularized distributional optimization problems. Machine Learning. 2024
Dai Hai Nguyen, Tetsuya Sakurai. Mirror variational transport: a particle-based algorithm for distributional optimization on constrained domains. Machine Learning. 2023
Dai Hai Nguyen, Koji Tsuda. On a linear fused Gromov-Wasserstein distance for graph structured data. Pattern Recognition. 2023. 138. 109351-109351
Dai Hai Nguyen, Koji Tsuda. Generating reaction trees with cascaded variational autoencoders. The Journal of Chemical Physics. 2022. 156. 4
A Particle-Based Algorithm for Distributional Optimization on Constrained Domains via Variational Transport and Mirror Descent
arXiv preprint arXiv:2208.00587 2022
A generative model for molecule generation based on chemical reaction trees
arXiv preprint arXiv:2106.03394 2021
Creative Complex Systems
Springer, Singapore 2021
Semi-supervised learning of hierarchical representations of molecules using neural message passing
arXiv preprint arXiv:1711.10168 2017
Lectures and oral presentations (6):
Mirror Variational Transport: A Particle-based Algorithm for Distributional Optimization on Constrained Domain
(ECML PKDD 2023 : European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases)
Learning Subtree Pattern Importance for Weisfeiler- Lehman based Graph Kernels
(ECML PKDD 2021 : European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2021)
ADAPTIVE: leArning DAta-dePendenT, concIse molecular VEctors for fast, accurate metabolite identification from tandem mass spectra
(27th International Conference on Intelligent Systems for Molecular Biology (ISMB/ECCB 2019) 2019)
SIMPLE: Sparse Interaction Model over Peaks of moLEcules for fast, interpretable metabolite identification from tandem mass spectra
(26th International Conference on Intelligent Systems for Molecular Biology (ISMB 2018) 2018)
Semi-supervised learning of hierarchical representations of molecules using neural message passing
(Machine Learning for Molecules and Materials in NIPS 2017 2017)