• 国立情報学研究所 情報学プリンシプル研究系 助教です。
• 興味: グラフ機械学習、最適輸送、推薦システム、検索システム
• 論文:
  1. Ryoma Sato, Shinji Ito. Influential Bandits: Pulling an Arm May Change the Environment. TMLR 2025. [arXiv]
  2. Ryoma Sato. Solving the Cold Start Problem on One’s Own as an End User via Preference Transfer. arXiv preprint 2025. [arXiv]
  3. Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada. Necessary and Sufficient Watermark for Large Language Models. TMLR 2025. [arXiv]
  4. Ryoma Sato. Overhead-free User-side Recommender Systems. arXiv preprint 2024. [arXiv]
  5. Yuki Takezawa, Han Bao, Ryoma Sato, Kenta Niwa, Makoto Yamada. Polyak Meets Parameter-free Clipped Gradient Descent. NeurIPS 2024. [arXiv]
  6. Ryoma Sato. Training-free Graph Neural Networks and the Power of Labels as Features. TMLR 2024. [arXiv]
  7. Ryoma Sato. Making Translators Privacy-aware on the User’s Side. TMLR 2024. [arXiv]
  8. Ryoma Sato, Yuki Takezawa, Han Bao, Kenta Niwa, Makoto Yamada. Embarrassingly Simple Text Watermarks. arXiv preprint 2023. [arXiv]
  9. Yuki Takezawa*, Ryoma Sato*, Han Bao, Kenta Niwa, Makoto Yamada. Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence. NeurIPS 2023. [arXiv]
  10. Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada. Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data. TMLR 2023. [arXiv]
  11. Ryoma Sato. Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure. ICML 2023. [arXiv]
  12. Ryoma Sato. Active Learning from the Web. WWW 2023. [arXiv]
  13. Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi. Approximating 1-Wasserstein Distance with Trees. TMLR 2022. [arXiv]
  14. Ryoma Sato. Towards Principled User-side Recommender Systems. CIKM 2022. [arXiv]
  15. Ryoma Sato. CLEAR: A Fully User-side Image Search System. CIKM 2022 (demo). [arXiv]
  16. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Twin Papers: A Simple Framework of Causal Inference for Citations via Coupling. CIKM 2022 (short). [arXiv]
  17. Mathis Petrovich, Chao Liang, Ryoma Sato, Yanbin Liu, Yao-Hung Hubert Tsai, Linchao Zhu, Yi Yang, Ruslan Salakhutdinov, Makoto Yamada. Feature Robust Optimal Transport for High-dimensional Data. ECML/PKDD 2022. [arXiv]
  18. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Re-evaluating Word Mover’s Distance. ICML 2022. [arXiv]
  19. Ryoma Sato. Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem. NAACL 2022 (short). [arXiv]
  20. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Poincare: Recommending Publication Venues via Treatment Effect Estimation. Journal of Informetrics 2022. [arXiv]
  21. Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada. Fixed Support Tree-Sliced Wasserstein Barycenter. AISTATS 2022. [arXiv]
  22. Ryoma Sato. Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data? SDM 2022. [arXiv]
  23. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Constant Time Graph Neural Networks. TKDD 2022. [arXiv]
  24. Ryoma Sato. Retrieving Black-box Optimal Images from External Databases. WSDM 2022. [arXiv]
  25. Ryoma Sato. Enumerating Fair Packages for Group Recommendations. WSDM 2022. [arXiv]
  26. Yuki Takezawa, Ryoma Sato, Makoto Yamada. Supervised Tree-Wasserstein Distance. ICML 2021. [arXiv]
  27. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Random Features Strengthen Graph Neural Networks. SDM 2021. [arXiv]
  28. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Fast Unbalanced Optimal Transport on a Tree. NeurIPS 2020. [arXiv]
  29. Ryoma Sato. A Survey on The Expressive Power of Graph Neural Networks. arXiv preprint 2020. [arXiv]
  30. Ryoma Sato, Marco Cuturi, Makoto Yamada, Hisashi Kashima. Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces. arXiv preprint 2020. [arXiv]
  31. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Approximation Ratios of Graph Neural Networks for Combinatorial Problems. NeurIPS 2019. [arXiv]
  32. Ryoma Sato, Makoto Yamada, Hisashi Kashima. Learning to Find Hard Instances of Graph Problems. ACML 2019. [arXiv]
  33. Ryoma Sato, Hisashi Kashima, Takehiro Yamamoto. Short-Term Precipitation Prediction with Skip-Connected PredNet. ICANN 2018.
• 書籍:
  • 佐藤竜馬『深層ニューラルネットワークの高速化』技術評論社．[Amazon]
  • 佐藤竜馬『グラフニューラルネットワーク（機械学習プロフェッショナルシリーズ）』講談社．[Amazon]
  • 佐藤竜馬『最適輸送の理論とアルゴリズム（機械学習プロフェッショナルシリーズ）』講談社．[Amazon]
• 講演一覧
• 受賞:
  • 2019 年度 IBISML 研究会賞
  • IBIS 2019 学生最優秀プレゼンテーション賞
  • NeurIPS 2019 Travel Award
• 学歴:
  • 京都大学 情報学研究科 博士（情報学） 2021-2024
    • 博士論文: User-Side Realization [arXiv]
  • 京都大学 情報学研究科 修士（情報学） 2019-2021
  • 京都大学 工学部 情報学科 学士（工学） 2015-2019
• 高校生・学部生の頃は競技プログラミングに熱中していました。
  • AtCoder : joisino
• そのほか活動（競技プログラミング関連）:
  • ACM-ICPC World Finals 2020 Coach
  • ACM-ICPC World Finals 2019 Contestant
  • ACM-ICPC Asia Jakarta Regional Contest 2018 2nd place (Gold Medal)
  • 国際情報オリンピック 2018 Host Technical Comittee
  • 国際情報オリンピック 2017 日本選手団副団長
  • 国際情報オリンピック 2014 銅メダル
  • 日本情報オリンピック 2014 金メダル
• GitHub / Google Scholar / dblp / Twitter / ブログ
• お問い合わせ：講演など、お仕事のご依頼は FlatMinima お問い合わせフォーム よりお問い合わせください。ご依頼の際は、ご予算、日程、規模感をお伝えいただければ幸いです。
• 趣味のページ