Research Scientist, NTT Communication Science Laboratories, NTT, Inc.
Visiting Associate Professor, Graduate School of Science and Technology, NAIST.
Visiting Scientist, Computational Physics Machine Learning Team, RIKEN Center for Advanced Intelligence Project, RIKEN.
ysk.tanaka [at] ntt.com
Machine learning (probabilistic models, Gaussian processes, point processes, deep learning, etc.)
Scientific machine learning (operator learning, physics-informed neural networks, neural ODEs etc.)
Data science (spatio-temporal data analysis, user modeling, etc.)
Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata, Naonori Ueda, Energy-consistent Neural Operators for Hamiltonian and Dissipative Partial Differential Equations, AISTATS, 2025.
Yeang Makara, Yusuke Tanaka, Takashi Matsubara, Takaharu Yaguchi, Learning Hamiltonian Partial Differential Equations Using DeepONet with A Symplectic Branch Network, SCML, 2025.
Baige Xu, Yusuke Tanaka, Takashi Matsubara, Takaharu Yaguchi, Learning Hamiltonian Density Using DeepONet for Modeling Wave Equations, SCML, 2025.
Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata, Naonori Ueda, Energy-consistent Neural Operator Learning, SCML, 2025.
Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato, Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective, NeurIPS, 2024.
Tomoharu Iwata, Yusuke Tanaka, Symplectic Neural Gaussian Processes for Meta-learning Hamiltonian Dynamics, IJCAI, pp. 4210 - 4218, 2024.
Baige Xu, Yusuke Tanaka, Takashi Matsubara, Takaharu Yaguchi, Operator Learning of Hamiltonian Density for Modeling Nonlinear Waves, SciCADE, 2024.
Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata, Naonori Ueda, Neural Operators for Hamiltonian and Dissipative PDEs, SciCADE, 2024.
Yusuke Tanaka, Learning Hamiltonian Dynamics Under Uncertainty via Symplectic Gaussian Processes, SCML, 2024.
Yusuke Tanaka, Tomoharu Iwata, Naonori Ueda, Symplectic Spectrum Gaussian Processes: Learning Hamiltonians from Noisy and Sparse Data, NeurIPS, 2022.
Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Hiroyuki Toda, Takeshi Kurashima, and Hisashi Kashima, Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes, KDD, Virtual Conference, pp. 1276 - 1286, 2021. (acceptance rate: 238/1541 = 15.4%)
Yasunori Akagi, Takuya Nishimura, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, Exact and Efficient Inference for Collective Flow Diffusion Model via Minimum Convex Cost Flow Algorithm, AAAI, New York, United States, pp. 3163 - 3170, 2020. (acceptance rate: 1591/7737 = 20.6%)
Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa, Hiroyuki Toda, Predicting Traffic Accidents with Event Recorder Data, ACM SIGSPATIAL Workshop on Prediction of Human Mobility (PredictGIS), Chicago, United States, pp. 11 - 14, 2019.
Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi, Hiroyuki Toda, Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs, NeurIPS, Vancouver, Canada, pp. 3000 - 3010, 2019. (acceptance rate: 1428/6743 = 21.2%) [poster], [code]
Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, Naonori Ueda, Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information, KDD, Anchorage, United States, pp. 373 - 383, 2019. (acceptance rate: 170/1200 = 14.2%)
Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa, Hiroyuki Toda, Refining Coarse-grained Spatial Data using Auxiliary Spatial Data Sets with Various Granularities, AAAI, Honolulu, United States, pp. 5091 - 5100, 2019. (acceptance rate: 1150/7095 = 16.2%) [slide, poster]
Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, Naonori Ueda, Estimating Latent People Flow without Tracking Individuals, IJCAI, Stockholm, Sweden, pp. 3556 - 3563, 2018. (acceptance rate: 710/3470 = 20.5%) [slide, poster]
Yusuke Tanaka, Takeshi Kurashima, Yasuhiro Fujiwara, Tomoharu Iwata, Hiroshi Sawada, Inferring Latent Triggers of Purchases with Consideration of Social Effects and Media Advertisements, WSDM, San Francisco, United States, pp. 543 - 552, 2016. (acceptance rate: 67/368 = 18.2%) [slide]
Naonori Ueda, Yusuke Tanaka, Akinori Fujino, Robust Naive Bayes Combination of Multiple Classifications, FMI, Fukuoka, Japan, pp. 141 - 155, 2013.
Takuya Kitamura, Shigeo Abe, Yusuke Tanaka, Multiple Nonlinear Subspace Methods Using Subspace-based Support Vector Machines, ICMLA, Honolulu, United States, pp. 358 - 363, 2011.
Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi, Hiroyuki Toda, Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains, Machine Learning, accepted. [code]
Zhong Chuang, Yusuke Tanaka, Tomoharu Iwata, Meta-Learning for Graphs with Heterogeneous Node Attribute Spaces for Few-Shot Edge Predictions, TMLR, Mar. 2025.
Lei Sun, Yusuke Tanaka, Tomoharu Iwata, Meta-Learning under Task Shift, TMLR, Oct. 2024.
Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, Hisashi Kashima, Context-aware spatio-temporal event prediction via convolutional Hawkes processes, Machine Learning, Mar. 2022.
Tomoharu Iwata, Yusuke Tanaka, Few-shot learning for spatial regression via neural embedding-based Gaussian processes, Machine Learning, Nov. 2021.
Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, Naonori Ueda, and Hisashi Kashima, Deep Mixture Point Processes: Spatio-temporal Event Prediction with External Factor, Journal of Japanese Society for Artificial Intelligence, Vol.36, No.5, p.C-L37_1-10, Sep. 2021 (in Japanese).
Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, Naonori Ueda, Toshiyuki Tanaka, Time-delayed Collective Flow Diffusion Models for Inferring Latent People Flow from Aggregated Data at Limited Locations, Artificial Intelligence, Vol. 292, 103430, Mar. 2021.
Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa, Hiroyuki Toda, Predicting Traffic Accidents with Dashboard Cameras, IPSJ-TOD, Vol. 14, No. 1, pp. 1 - 7, Jan. 2021. (in Japanese)
Maya Okawa, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, Tomohiro Yamada, Marked Temporal Point Processes for Trip Demand Prediction in Bike Sharing Systems, IEICE Trans. Inf. & Syst., Vol. E102-D, No. 9, pp. 1635-1643, Sep. 2019.
Yusuke Kawai, Yusuke Tanaka, Hiroyuki Toda, Yoshiharu Ishikawa, Estimating People Flow from a Large Amount of Aggregated Data with a Few Tracking Data, DBSJ Japanese Journal, Vol.17-J, No. 7, Mar. 2019. (in Japanese)
Yusuke Tanaka, Takeshi Kurashima, Yasuhiro Fujiwara, Tomoharu Iwata, Hiroshi Sawada, Identifying Latent Triggers of Purchases with Consideration of Social Effects and Media Advertisements, IPSJ Journal, Vol. 58, No. 2, pp. 580 - 593, Feb. 2017. (in Japanese)
Yusuke Tanaka, Naonori Ueda, Toshiyuki Tanaka, Bayesian Classifier Based on Class-specific Feature Selection, IEICE Trans. Inf. & Syst., Vol. J96-D, No. 11, pp. 2755 − 2764, Nov. 2013. (in Japanese)
Baige Xu, Yusuke Tanaka, Takashi Matsubara, Takaharu Yaguchi, Learning Hamiltonian Density Using DeepONet, arXiv preprint arXiv:2502.19994, 2025.
Yoshiaki Takimoto, Yusuke Tanaka, Tomoharu Iwata, Maya Okawa, Hideaki Kim, Hiroyuki Toda, Takeshi Kurashima, Meta-learning for Neural Network-based Temporal Point Processes, arXiv:2401.15846, 2024.
Tomoharu Iwata, Yusuke Tanaka, Naonori Ueda, Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEs, arXiv:2310.13270, 2023.
Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi, Hiroyuki Toda, Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains, arXiv:2206.12141, 2022. [code]
Yasunori Akagi, Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, Probabilistic Optimal Transport based on Collective Graphical Models, arXiv:2006.08866, 2020.
Advisor, NTT Summer Internship, 2017, 2024, 2025.
Visiting Associate Professor, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Apr. 2021 -
Yusuke Tanaka, Neural Operator Learning based on Spectral Representation of Hamiltonian Partial Differential Equations, REMODEL-DSC Workshop on Differential Equations, Geometry and Machine Learning, Kobe University, 2025.
Yusuke Tanaka, Energy-Consistent Neural Operator Learning, Workshop on Mathematics for Machine Learning and Its Application to Industry, Kyushu University, 2025.
Yusuke Tanaka, Neural operator learning for Hamiltonian and dissipative PDEs, Workshop on Dynamical Systems and Machine Learning, RIKEN Center of API, 2025.
Yusuke Tanaka, Machine Learning Models for Hamiltonian and Dissipative Systems, Data Science and Computational Statistics Seminar, University of Birmingham, 2024.
Yusuke Tanaka, Gaussian Processes for Spatio-temporal Data Analysis, REMODEL-DSC Workshop on Machine Learning and Physics, Hokkaido University, 2024.
Yusuke Tanaka, Inferring Latent People Flows from Aggregated Data in Real-world Settings, ISCIE SSS, 2018.
Reviewer, Transactions on Machine Learning Research (TMLR), 2022-
Program Committee Member, WSDM, 2022, 2023.
Reviewer, ICLR, 2021, 2022, 2023, 2024, 2025, 2026.
Reviewer, ICML, 2020 (top reviewers), 2021, 2022, 2023, 2024, 2025, 2026.
Program Committee Member, IJCAI, 2020, 2022.
Program Committee Member, AAAI, 2024, 2025, 2026.
Reviewer, NeurIPS, 2019 (top reviewers), 2020, 2021, 2022, 2023, 2024, 2025.
Dec. 2020 - Present, Research scientist at NTT Communication Science Laboratories, NTT Corporation, Japan
Apr. 2017 - Mar. 2020, Doctor of Informatics, Kyoto University (Supervisor: Dr. Toshiyuki Tanaka)
Apr. 2013 - Nov. 2020, Researcher at NTT Service Evolution Laboratories, NTT Corporation, Japan
Apr. 2011 - Mar. 2013, Master of Informatics, Kyoto University (Supervisor: Dr. Naonori Ueda, Dr. Toshiyuki Tanaka)
Apr. 2007 – Mar. 2011, Bachelor of Engineering, Kobe University (Supervisor: Dr. Shigeo Abe)
Yusuke Tanaka, Probabilistic Models for Spatially Aggregated Data, Doctoral Thesis, Graduate School of Informatics, Kyoto University, 2020. [slide]
Yusuke Tanaka, Bayesian Classifier based on Class-Specific Feature Selection, Master's Thesis, Graduate School of Informatics, Kyoto University, 2013.