Publications

International Conference

  1. Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Kazuki Adachi, Yasuhiro Fujiwara,
    Positive-unlabeled AUC Maximization under Covariate Shift,
    ICML, 2025.
  2. Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka, Tomoya Yamashita,
    Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation,
    ICLR, 2025.
    [paper]
  3. Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Yasuhiro Fujiwara,
    Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation,
    AISTATS, 2025.
  4. Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Yasuhiro Fujiwara,
    AUC Maximization under Positive Distribution Shift,
    NeurIPS, 2024.
    [paper]
  5. Sekitoshi Kanai, Shin’ya Yamaguchi, Masanori Yamada, Hiroshi Takahashi, Yasutoshi Ida,
    One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training,
    ICML, 2023.
    [paper] [arXiv]
  6. Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Yasuhiro Fujiwara,
    Meta-learning for Robust Anomaly Detection,
    AISTATS, 2023.
    [paper]
  7. Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Sekitoshi Kanai, Masanori Yamada, Yuuki Yamanaka, Hisashi Kashima,
    Learning Optimal Priors for Task-Invariant Representations in Variational Autoencoders,
    KDD, 2022.
    [paper] [slide] [slide(ja)] [poster] [poster(ja)]
  8. Sekitoshi Kanai, Masanori Yamada, Shin’ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida,
    Constraining Logits by Bounded Function for Adversarial Robustness,
    IJCNN, 2021.
    [paper] [arXiv]
  9. Yuki Yamanaka, Tomoharu Iwata, Hiroshi Takahashi, Masanori Yamada, Sekitoshi Kanai,
    Autoencoding Binary Classifiers for Supervised Anomaly Detection,
    PRICAI, 2019.
    [paper] [arXiv]
  10. Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka, Masanori Yamada, Satoshi Yagi,
    Variational Autoencoder with Implicit Optimal Priors,
    AAAI, 2019.
    [paper] [arXiv] [code] [slide] [poster]
  11. Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka, Masanori Yamada, Satoshi Yagi,
    Student-t Variational Autoencoder for Robust Density Estimation,
    IJCAI, 2018.
    [paper] [code] [slide]

Preprints

  1. Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuki Yamanaka,
    Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data,
    arXiv:2405.18929, 2024.
    [arXiv] [poster(ja)]
  2. Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi, Yuki Yamanaka, Yasutoshi Ida,
    Smoothness Analysis of Loss Functions of Adversarial Training,
    arXiv:2103.01400, 2021.
    [arXiv]
  3. Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata, Tomokatsu Takahashi, Yuki Yamanaka, Hiroshi Takahashi, Atsutoshi Kumagai,
    Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression,
    arXiv:2102.02950, 2021.
    [arXiv]

Journal

  1. Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi, Yuki Yamanaka, Yasutoshi Ida,
    Relationship Between Nonsmoothness in Adversarial Training, Constraints of Attacks, and Flatness in the Input Space,
    IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2023.3244172.
    [paper]
  2. 高橋大志, 岩田具治, 山中友貴, 山田真徳, 八木哲志, 鹿島久嗣,
    Student-t VAEによるロバスト確率密度推定,
    人工知能学会論文誌, 2021, 36 巻, 3 号, p. A-KA4_1-9.
    [paper]

Thesis

Contents (Written in Japanese)