Associate Professor at Graduate School of Engineering Science, Osaka University.

The research interests are in Bayesian and geometric inductive bias for data-driven modeling. A data-driven method builds an accurate decision maker from data. In contrast, a mathematical model is designed to ensure properties of targets, such as a dependency between factors, uncertainty, a geometric symmetry, and laws of physics. My purpose is to design deep learning architectures to ensure these properties, thereby balancing the qualitative property based on the prior knowledge and the quantitative accuracy learned from data. See projects for more details.

Keywords: geometric deep learning, Bayesian deep learning

We are hiring post-doctoral researchers and doctoral students in the above fields. Please contact me.

e-mail: matsubara@sys.es.osaka-u.ac.jp

Google Scholar / DBLP / researchmap / Twitter


Recent Papers


Recent Activities

  • On Mar. 2022, our paper “Imbalance-Aware Learning for Deep Physics Modeling,” co-authored with Mr. Yoshida and Prof. Yaguchi, has been accepted at ICLR2022 Workshop on AI for Earth and Space Science (ai4earth).
  • On Dec. 2021, our paper “KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss,” co-authored with Ms. Chen and Prof. Yaguchi, has been accepted at AAAI Conference on Artificial Intelligence (AAAI) (acceptance rate 1,349/9,020=15.0%, oral 387/9,020=4.3%).
  • On Sep. 2021, our paper “Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory,” co-authored with Prof. Miyatake and Prof. Yaguchi, has been accepted at Neural Information Processing Systems (NeurIPS) (acceptance rate 26%). The proposed adjoint method based on a symplectic integrator obtains a gradient of an ODE with much less memory than the naive backpropagation algorithm and checkpointing schemes and faster than the ordinary adjoint method in practice.
  • On Sep. 2021, our paper “Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems,” co-authored with Ms. Chen and Prof. Yaguchi, has been accepted at Neural Information Processing Systems (NeurIPS) as a spotlight (3%).
  • On Jul. 2021, our paper “ChartPointFlow for Topology-Aware 3D Point Cloud Generation,” co-authored with Mr. Kimura and Prof. Uehara, has been accepted at ACM International Conference on Multimedia (ACMMM) as an oral presentation (179/1,942=9.2%). Our proposed model assigns a conditioned map to each continuous subset of a point cloud, similarly to a chart of a manifold, thereby nicely generating point clouds with different topologies.
  • On Apr. 2021, our paper “Deep Discrete-Time Lagrangian Mechanics,” co-authored with Mr. Aoshima and Prof. Yaguchi, is accepted at ICLR2021 Workshop on Deep Learning for Simulation (SimDL).
  • On Oct. 2020, our paper “The Error Analysis of Numerical Integrators for Deep Neural Network Modeling of Differential Equations,” co-authored with Mr. Terakawa and Prof. Yaguchi, has been accepted at NeurIPS2020 Workshop on Machine Learning and the Physical Sciences (ML4PS).
  • On Sep. 2020, our paper “Deep Energy-based Modeling of Discrete-Time Physics,” co-authored with Dr. Ishikawa and Prof. Yaguchi, has been accepted at Neural Information Processing Systems (NeurIPS) as an oral presentation (105/9,454=1.1%). For modeling physical dynamical systems by neural networks, this study proposes the automatic discrete differentiation algorithm, which ensures the energy conservation and dissipation laws in discrete time.
  • On Sep. 2020, our paper “Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity” has been accepted at IEEE Transactions on Cybernetics. This study proposes the unregularized score, which detects anomalous samples robustly to their intrinsic uncertainty.
  • On Sep. 2020, our paper “Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task,” co-authored with Prof. Cai at Monash University, has been accepted at ACM Transactions on Multimedia Computing, Communications, and Applications.
  • On Jul. 2020, our paper “Deep Generative Model of Individual Variability in fMRI Images of Psychiatric Patients” has been accepted at IEEE Transactions on Biomedical Engineering. This study proposes a deep generative model of fMRI images with psychiatric disorders and individual variability as causes, thereby giving a more accurate diagnosis of the disorders.