Nguyen Duc Thien


PhD Student
Department of Information and Communications Engineering, Institute of Science Tokyo (formerly TokyoTech)

Research

Machine Learning, Data Science, Signal Processing

Education

Ph.D. (April 2024 -- Now)
Institute of Science Tokyo (formerly TokyoTech), Japan
Advisor: Prof. Konstantinos Slavakis [website]

MEng. (April 2022 -- March 2024)
Institute of Science Tokyo (formerly TokyoTech), Japan
Advisor: Prof. Konstantinos Slavakis [website]

BEng. (April 2018 -- March 2022)
Institute of Science Tokyo (formerly TokyoTech), Japan
Thesis: Multi-city spatial projection of a dengue vector’s suitability considering urbanization and climate change
Advisor: Prof. Alvin C.G. Varquez [website]

Undergraduate (August 2017 -- March 2018)
University of Engineering and Technology, Vietnam National University, Ha Noi, Viet Nam
Computer Science

Work Experience

Credit Scoring Team, Rakuten Group (August 2025 -- Now)
Research Scientist, Tokyo, Japan

[Tensor Learning Team], RIKEN AIP (April 2024 -- March 2025)
Junior Research Associate, Tokyo, Japan

FPT Japan (April 2022 -- March 2024)
Machine Learning Engineer, Tokyo, Japan

Visual Alpha (April 2020 -- April 2022)
Frontend Developer, Part-time, Tokyo, Japan

Publications

Pre-prints

  1. Duc Thien Nguyen, Konstantinos Slavakis, Eleftherios Kofidis, and Dimitris Pados. Kernel regression with tensor trains and Hadamard overparameterization. arXiv:2607.17390.

  2. Guang Lin*, Duc Thien Nguyen*, Zerui Tao, Konstantinos Slavakis, Toshihisa Tanaka, Qibin Zhao. Model-free adversarial purification via coarse-to-fine tensor network representation. arXiv:2502.17972.

Peer-reviewed Journals

  1. Duc Thien Nguyen, Konstantinos Slavakis, and Dimitris Pados. Imputation of time-varying edge flows in graphs by multilinear kernel regression and manifold. Signal Processing, vol. 237, pp. 110077, December 2025.

  2. Duc Thien Nguyen and Konstantinos Slavakis. Multilinear kernel regression and imputation via manifold learning. IEEE Open Journal of Signal Processing, vol. 5, pp. 1073-1088, 2024.

Peer-reviewed Conferences

  1. Duc Thien Nguyen, Konstantinos Slavakis, Eleftherios Kofidis, and Dimitris Pados. Kernel regression via tensor trains with Hadamard overparametrization and imputation of dynamic graph edge flows. ICASSP 2026, pp. 341-345, Barcelona, Spain, 3-8 May, 2026.

  2. Duc Thien Nguyen, Konstantinos Slavakis, and Dimitris Pados. Estimating dynamic graph flows with kernel models and Hadamard-structured Riemannian constraints. APSIPA ASC 2025, pp. 1538-1543, Shangri-la, Singapore, 22-24 October, 2025.

  3. Duc Thien Nguyen and Konstantinos Slavakis. Multilinear kernel regression and imputation via manifold learning: The dynamic MRI case. ICASSP 2024, pp. 9466-9470, Seoul, Korea, 14-19 April, 2024.

  4. Duc Thien Nguyen*, Manh Duc Tuan Nguyen*, Truong Son Hy*, and Risi Kondor. Fast Temporal Wavelet Graph Neural Networks. NeurIPS 2023 (NeurReps Workshop).

Non-peer-reviewed Conferences

  1. Duc Thien Nguyen and Konstantinos Slavakis. Estimating dynamic graph flows with kernel models and Hadamard-structured Riemannian constraints. SIP 2025, Japan.

  2. Duc Thien Nguyen, Konstantinos Slavakis, and Dimitris Pados. Imputation of time-varying edge flows in graphs by multilinear kernel regression and manifold learning. SIP 2024, Japan.

  3. Duc Thien Nguyen and Konstantinos Slavakis. Multi-linear kernel regression and imputation in data manifolds. SIP 2023, Japan.