Biography
I’m a third-year Ph.D. student in Computer Science at Cornell University, where I’m fortunate to be advised by Prof. Thorsten Joachims. I completed my bachelor’s degree in Industrial Engineering and Economics at the Tokyo Institute of Technology.
My research lies at the intersection of machine learning and causal inference called counterfactual learning. I am interested in the counterfactual nature of logged bandit feedback and human behavior data obtained from interactive systems, and ways of using biased real-world datasets to assist safe and better decision making in the wild.
Download my CV here
Interests
- Counterfactual Evaluation
- Learning from Behavior Data
- Statistical Machine Learning
- Fairness in Ranking
Education
-
PhD in Computer Science, 2021 -
Cornell University
-
B.Eng in Industrial Engineering, 2016 - 2021
Tokyo Institute of Technology
Featured Publications
(2024).
Long-term Off-Policy Evaluation and Learning.
In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).
(2023).
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior.
In Proceedings of the 29th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (Acceptance rate=22.3%).
(2023).
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling.
In Proceedings of the 40th International Conference on Machine Learning (ICML) (Acceptance rate=27.9%).
(2022).
Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking.
In Proceedings of the 28th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (Acceptance rate=14.9%).
(2022).
Off-Policy Evaluation for Large Action Spaces via Embeddings.
In Proceedings of 39th International Conference on Machine Learning (ICML) (Acceptance rate=21.9%).
(2022).
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model.
In Proceedings of the 15th International Conference on Web Search and Data Mining (WSDM) (Acceptance rate=20.2%, Best Paper Runner-Up Award).
(2021).
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation.
In Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks.
(2020).
Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback.
In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM) (Acceptance rate=14.8%).
Recent Publications
Quickly discover relevant content by filtering publications.
(2024).
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction.
In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).
(2024).
Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems.
In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).
(2024).
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation.
In Proceedings of the Twelfth International Conference on Learning Representations (ICLR) (Acceptance Rate=31%).
(2022).
Policy-Adaptive Estimator Selection for Off-Policy Evaluation.
In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI) (Acceptance rate=19.6%).
(2022).
Counterfactual Evaluation and Learning for Interactive Systems.
In Proceedings of the 28th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD).
Awards
Paper Awards
- WSDM2022 Best Paper Runner-Up Award
- Paper: Haruka Kiyohara, Yuta Saito, Tatsuya Matsuhiro, Yusuke Narita, Nobuyuki Shimizu, and Yasuo Yamamoto. Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model.
Outstanding Reviewer Awards
Other Awards
- Forbes Japan 30 Under 30 2022
- Japan Open Innovation Prize 2021 Prime Minister Award
Scholarships
- Masason Foundation Fellowship
- Funai Overseas Scholarship
- Doctoral fellowship by the Funai Foundation (a private foundation in Japan).
- Granted two full years of tuition plus a monthly stipend of $3,000.
Relevant Courses
Fall 2023
- CS6410: Advanced Systems
- CS6784: Machine Learning in Feedback Systems
Spring 2022
- ORIE6170: Engineering Societal Systems
Fall 2021
- CS6787: Advanced Machine Learning Systems
- CS7792: Fairness and Dynamics of Learning Systems
Academic Service
Conference Program Committee
- KDD: 2022, 2023
- AAAI: 2023
- ICLR: 2022
- RecSys: 2023
- WSDM: 2022, 2023
- NeurIPS: 2021, 2022, 2023
- ICML: 2021, 2022, 2023
- AISTATS: 2021
Workshop Organizer
- RecSys 2023 WS on Causality, Counterfactuals, Sequential Decision-Making & Reinforcement Learning
- RecSys 2022 WS on Causality, Counterfactuals, Sequential Decision-Making & Reinforcement Learning
Workshop Program Committee
- ICML 2023 WS on Interactive Learning with Implicit Human Feedback
- NeurIPS 2022 WS on Offline Reinforcement Learning
- NeurIPS 2022 WS on Reinforcement Learning for Real Life
- NeurIPS 2021 WS on Offline Reinforcement Learning
- NeurIPS 2021 WS on Causal Inference Challenges in Sequential Decision Making
Journal Reviewer
- ACM Transactions on Intelligent Systems and Technology (TIST)
- ACM Transactions on Information Systems (TOIS)
- ACM Transactions on Recommender Systems (TORS)
- IEEE Transactions on Knowledge and Data Engineering (TKDE)
- Transactions on Machine Learning Research (TMLR)
Contact
- ys552 AT cornell.edu
- G33 Gates Hall, Cornell University, Ithaca, NY 14850