Publications & Awards


  • Artificial Neural Networks Applied as Molecular Wave Function Solvers
    Peng-Jian, Y., Sugiyama, M., Tsuda, K., Yanai, T.   Journal of Chemical Theory and Computation, 2020.
    [BibTeX]  [DOI: 10.1021/acs.jctc.9b01132]
  • Testing Machine Learning Code Using Polyhedral Region
    Ahmed, M. S., Ishikawa, F., Sugiyama, M.   The 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020), Visions and Reflections Track, 2020. (accepted)
  • Coordinate Descent Method for Log-Linear Model on Posets
    Hayashi, S., Sugiyama, M., Matsushima, S.   The 7th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2020), 2020. (accepted)


  • Legendre Decomposition for Tensors
    Sugiyama, M., Nakahara, H., Tsuda, K.   Journal of Statistical Mechanics: Theory and Experiment, 2019.
    [BibTeX]  [Paper]  [DOI: 10.1088/1742-5468/ab3196]
  • Summarizing Significant Subgraphs by Probabilistic Logic Programming
    Bellodi, E., Sato, K., Sugiyama, M.   Intelligent Data Analysis, 2019.
    [BibTeX]  [DOI: 10.3233/IDA-184339]
  • Finding Statistically Significant Interactions between Continuous Features
    Sugiyama, M., Borgwardt, K.M.   The 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), 2019.
    [BibTeX]  [arXiv]  [Paper]  [Code]  [Slide]  [Poster]  [DOI: 10.24963/ijcai.2019/484]
  • Bias-Variance Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions
    Luo, S., Sugiyama, M.   The 33rd AAAI Conference on Artificial Intelligence (AAAI-19), 2019.
    [BibTeX]  [arXiv]  [Paper]  [Code]  [DOI: 10.1609/aaai.v33i01.33014488]


  • graphkernels: R and Python Packages for Graph Comparison
    Sugiyama, M., Ghisu, E., Llinares-López, F., Borgwardt, K.M.   Bioinformatics, 34(3), 530—532, 2018
    [BibTeX]  [Paper]  [Library (R)]  [Library (Python)]  [DOI: 10.1093/bioinformatics/btx602
  • Legendre Decomposition for Tensors
    Sugiyama, M., Nakahara, H., Tsuda, K.   Advances in Neural Information Processing Systems (NeurIPS2018), 2018.
    [BibTeX]  [arXiv]  [Paper]  [Code]  [Slide]  [Poster]  [Video]
  • Learning Graph Representation via Formal Concept Analysis
    Yoneda, Y., Sugiyama, M., Washio, T.   NeurIPS 2018 Workshop on Relational Representation Learning, 2018.
    [BibTeX]  [arXiv]
  • 2018 JSAI Incentive Award
    Yoneda, Y., Sugiyama, M., Washio, T.


  • Tensor Balancing on Statistical Manifold
    Sugiyama, M., Nakahara, H., Tsuda, K.   The 34th International Conference on Machine Learning (ICML 2017), 2017.
    [BibTeX]  [arXiv]  [Paper]  [Code]  [Slide]  [Poster]  [Video]
  • Searching for Bacterial Pathogens in the Digital Ocean—Executive Summary
    Giuliano, L., Dorman, C., Bowler, C., Sugiyama, M., Vezzulli, L., Czerucka, D., Le Roux, F., D'Auria, G., Troussellier, M., Briand, F.   CIESM Workshop Monograph, 49, 5–25, 2017.
    [BibTeX]  [Paper]
  • Finding Statistically Significant Patterns from Data
    Sugiyama, M.   CIESM Workshop Monograph, 49, 53–58, 2017.
  • Pattern Mining with Statistical Significance (in Japanese)
    Sugiyama, M.   Communications of the Operations Research Society of Japan, 62(4), 226–232, 2017.
    [BibTeX]  [Paper]
  • 2017 JSAI Incentive Award
    Sugiyama, M., Nakahara, H., Tsuda, K.

© Mahito Sugiyama 2020