Satoshi Hara - Publication

Refereed Journal Papers

Naoyuki Terashita, Satoshi Hara.
Variance Reduction of Stochastic Hypergradient Estimation by Mixed Fixed-Point Iteration
Transactions on Machine Learning Research, 2025.
Daisuke Hatano, Satoshi Hara, Hiromi Arai.
Path-Specific Counterfactual Fairness via Dividend Correction
Transactions on Machine Learning Research, 2025.
Taichi Tomono, Satoshi Hara, Junko Iida, Takashi Washio.
Enhancing constituent estimation in nucleic acid mixture models using spectral annealing inference and MS/MS information
Frontiers in Analytical Science (Chemometrics), 5, 2025.
Naoyuki Terashita, Hiroki Ohashi, Satoshi Hara.
Data Cleansing for GANs
IEEE Transactions on Neural Networks and Learning Systems, 2025.
Satoshi Hara, Mitsuru Matsuura, Junya Honda, Shinji Ito.
Active Model Selection: A Variance Minimization Approach
Special Issue for ACML 2024, Machine Learning, 2024.
Taichi Tomono, Satoshi Hara, Yusuke Nakai, Kazuma Takahara, Junko Iida, Takashi Washio.
A Bayesian Approach for Component Estimation in Nucleic Acid Mixture Models
Frontiers in Analytical Science (Chemometrics), 3, 2023.
Tomohisa Kumagai, Kazuma Suzuki, Akiyoshi Nomoto, Satoshi Hara, Akiyuki Takahashi.
Prediction of the binding energy of self interstitial atoms in alpha iron by a graph neural network
Materialia, 33, 101977, 2024.
Takashi Kojima, Takashi Washio, Satoshi Hara, Masataka Koishi.
Search strategy for rare microstructure to optimize material properties of filled rubber using machine learning based simulation
Computational Materials Science 204, 111207,2022.
Masaru Kondo, Akimasa Sugizaki, Md. Imrul Khalid, H. D. P. Wathsala, Kazunori Ishikawa, Satoshi Hara, Takayuki Takaai, Takashi Washio, Shinobu Takizawa, Hiroaki Sasai,
Energy-, time-, and labor-saving synthesis of α-ketiminophosphonates: machine-learning-assisted simultaneous multiparameter screening for electrochemical oxidation
Green Chemistry 23(16):5825-5831 ,2021.
Takashi Kojima, Takashi Washio, Satoshi Hara, Masataka Koishi.
Synthesis of computer simulation and machine learning for achieving the best material properties of filled rubber
Scientific Reports 10, 18127, 2020.
Masaru Kondo, H.D.P. Wathsala, Makoto Sako, Yutaro Hanatani, Kazunori Ishikawa, Satoshi Hara, Takayuki Takaai, Takashi Washio, Shinobu Takizawa, Hiroaki Sasai.
Efficient prediction of flow reaction conditions using machine-learning for sequential Rauhut-Currier and [3+2] annulation
Chemical Communication, 8(56):1259-1262, 2020.
Hirofumi Ohta, Kengo Kato, Satoshi Hara.
Quantile Regression Approach to Conditional Mode Estimation
Electronic Journal of Statistics. 13(2):3120-3160, 2019. [arXiv1, 2]
Hiroki Yanagisawa and Satoshi Hara.
Discounted Average Degree Density Metric and New Algorithms for the Densest Subgraph Problem
Networks, 71(1):3--15, 2018.
Satoshi Hara, Takafumi Ono, Ryo Okamoto, Takashi Washio, and Shigeki Takeuchi.
Quantum-State Anomaly Detection for Arbitrary Errors Using a Machine-Learning Technique
Physical Review A, 94(4):042341, 2016.
Satoshi Hara, Takafumi Ono, Ryo Okamoto, Takashi Washio, and Shigeki Takeuchi.
Anomaly Detection in Reconstructed Quantum States Using a Machine-Learning Technique
Physical Review A, 89(2):022104, 2014. [arXiv]
Satoshi Hara and Takashi Washio.
Learning a Common Substructure of Multiple Graphical Gaussian Models
Neural Networks, 38:23--38, 2013. [arXiv]
Satoshi Hara, Yoshinobu Kawahara, Takashi Washio, Paul Von Bünau, Terumasa Tokunaga, and Kiyohumi Yumoto.
Separation of Stationary and Non-Stationary Sources with a Generalized Eigenvalue Problem
Neural Networks, 33:7--20, 2012.

Refereed Conference Papers

Kentaro Kanamori, Ken Kobayashi, Satoshi Hara, Takuya Takagi.
Algorithmic Recourse for Long-Term Improvement
In Proceedings of the 42nd International Conference on Machine Learning (ICML'25), 2025.
Yudai Yamamoto, Satoshi Hara.
Fast Stealthily Biased Sampling Using Sliced Wasserstein Distance
In Proceedings of the 16th Asian Conference on Machine Learning (ACML'24), 2024. Best Paper Award
Hirofumi Suzuki, Hiroaki Iwashita, Takuya Takagi, Yuta Fujishige, Satoshi Hara.
Rule Mining for Correcting Classification Models
In Proceedings of the 2023 IEEE International Conference on Data Mining (ICDM'23), pages 1331--1336, 2023. [arXiv]
Satoshi Hara, Yuichi Yoshida.
Average Sensitivity of Decision Tree Learning
The 11th International Conference on Learning Representations (ICLR'23), 2023.
Gabriel Laberge, Ulrich Aïvodji, Satoshi Hara, Mario Marchand, Foutse Khomh.
Fooling SHAP with Stealthily Biased Sampling
The 11th International Conference on Learning Representations (ICLR'23), 2023.
Hirofumi Suzuki, Hiroaki Iwashita, Takuya Takagi, Keisuke Goto, Yuta Fujishige, Satoshi Hara.
Explainable and Local Correction of Classification Models Using Decision Trees
In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI'22), pages 8404--8413, 2022.
Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs, Satoshi Hara.
Characterizing the risk of fairwashing
Advances in Neural Information Processing Systems 34 (NeurIPS'21), 2021. [OpenReview][arXiv][code]
Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui.
Evaluation of Similarity-based Explanations
The 9th International Conference on Learning Representations (ICLR'21), 2021. [arXiv][code]
Danqing Pan, Tong Wang, Satoshi Hara.
Interpretable Companions for Black-Box Models
In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS'20), pages 2444--2454, 2020. [arXiv][code][slide&video]
Kazuto Fukuchi, Satoshi Hara, Takanori Maehara.
Faking Fairness via Stealthily Biased Sampling
In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI'20), pages 412--419, 2020. [arXiv][code][slide][IEEE Spectrum]
Satoshi Hara, Atsuhi Nitanda, Takanori Maehara.
Data Cleansing for Models Trained with SGD
Advances in Neural Information Processing Systems 32 (NeurIPS'19), 2019. [arXiv][code][slide]
Satoshi Hara, Weichih Chen, Takashi Washio, Tetsuichi Wazawa, Takeharu Nagai.
SPoD-Net: Fast Recovery of Microscopic Images Using Learned ISTA
In Proceedings of the 11th Asian Conference on Machine Learning (ACML'19), pages 694--709, 2019. [code]
Satoshi Hara, Takanori Maehara.
Convex Hull Approximation of Nearly Optimal Lasso Solutions
In Proceedings of 16th Pacific Rim International Conference on Artificial Intelligence, Part II, pages 350--363, 2019. [arXiv][code][slide]
Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau, Sébastien Gambs, Satoshi Hara, Alain Tapp.
Fairwashing: the risk of rationalization
In Proceedings of the 36th International Conference on Machine Learning (ICML'19), pages 161--170, 2019. [arXiv][code][poster][slide&video][IEEE Spectrum]
Satoshi Hara and Kohei Hayashi.
Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach
In Proceedings of the 21th International Conference on Artificial Intelligence and Statistics (AISTATS'18), pages 77--85, 2018. [arXiv][code][poster]
Satoshi Hara and Masakazu Ishihata.
Approximate and Exact Enumeration of Rule Models
In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), pages 3157--3164, 2018. [poster]
Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa, Takafumi Ono, Ryo Okamoto, and Shigeki Takeuchi.
Consistent and Efficient Nonparametric Different-Feature Selection
In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS'17), pages 130--138, 2017. [poster]
Satoshi Hara and Takanori Maehara.
Enumerate Lasso Solutions for Feature Selection
In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI'17), pages 1985--1991, 2017. [code][poster]
Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, and Taiji Suzuki.
A Consistent Method for Graph Based Anomaly Localization
In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS'15), pages 333--341, 2015.
Satoshi Hara, Rudy Raymond, Tetsuro Morimura, and Hidemasa Muta.
Predicting Halfway Through Simulation: Early Scenario Evaluation Using Intermediate Features of Agent-Based Simulations
In Proceedings of the 2014 Winter Simulation Conference (WSC'14), pages 334--343, 2014.
Hidemasa Muta, Rudy Raymond, Satoshi Hara, and Tetsuro Morimura.
A Multi-Objective Genetic Algorithm Using Intermediate Features of Simulations
In Proceedings of the 2014 Winter Simulation Conference (WSC'14), pages 793--804, 2014.
Satoshi Hara and Takashi Washio.
Group Sparse Inverse Covariance Selection with a Dual Augmented Lagrangian Method
In Neural Information Processing, Lecture Notes in Computer Science (ICONIP'12), pages 108--115, 2012.
Satoshi Hara and Takashi Washio.
Common Substructure Learning of Multiple Graphical Gaussian Models
In Machine learning and knowledge discovery in databases (ECML PKDD'11), pages 1--16. 2011.
Satoshi Hara, Yoshinobu Kawahara, Takashi Washio, and Paul von Bünau.
Stationary Subspace Analysis as a Generalized Eigenvalue Problem
In Neural Information Processing. Theory and Algorithms, Lecture Notes in Computer Science (ICONIP'10), pages 422--429, 2010.
Masashi Sugiyama, Satoshi Hara, Paul Von Bünau, Taiji Suzuki, Takafumi Kanamori, and Motoaki Kawanabe.
Direct Density Ratio Estimation with Dimensionality Reduction
In Proceedings of the 10th SIAM International Conference on Data Mining (SDM'10), pages 595--606, 2010.

Invited Talks

On Multiplicity of Explanation. Japanese-American-German Frontiers of Science Symposium (JAGFOS), 2023.
Explanation in Machine Learning and Its Reliability. NeurIPS Meetup Japan 2021.

Workshop Papers

Mitsuru Matsuura, Satoshi Hara.
Active Model Selection: A Variance Minimization Approach
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World. 2023.
Takuma Ochiai, Keiichiro Seno, Kota Matsui, Satoshi Hara.
Active Testing of Binary Classification Model Using Level Set Estimation
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World. 2023.
Naoyuki Terashita, Satoshi Hara.
Cooperative Personalized Bilevel Optimization over Random Directed Networks
The 14th Workshop on Optimization and Learning in Multiagent Systems. 2023.
Satoshi Hara, Kouichi Ikeno, Tasuku Soma, Takanori Maehara.
Maximally Invariant Data Perturbation as Explanation
In Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), pages 54--58, 2018. [code][slide][poster]
Satoshi Hara and Takanori Maehara.
Finding Alternate Features in Lasso
In Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems, 2016. [code][poster]
Satoshi Hara and Kohei Hayashi.
Making Tree Ensembles Interpretable
In Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), pages 81--85, 2016. [poster] Best paper runner-up
Satoshi Hara and Takashi Washio.
Anomalous Neighborhood Selection
In Proceedings of the 12th IEEE International Conference on Data Mining Workshops (ICDMW), pages 474--480, 2012.

Technical Reports

Hiroki Yanagisawa and Satoshi Hara.
Axioms of Density: How to Define and Detect the Densest Subgraph
IBM Research Technical Report, 2016.

Preprints

Naoyuki Terashita, Satoshi Hara.
Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks
arXiv:2210.02129, 2022.
Kentaro Kanamori, Satoshi Hara, Masakazu Ishihata, Hiroki Arimura.
Enumeration of Distinct Support Vectors for Interactive Decision Making
arXiv:1906.01876, 2019.
Kouichi Ikeno, Satoshi Hara.
Maximizing Invariant Data Perturbation with Stochastic Optimization
arXiv:1807.05077, 2018. [code]
Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa, Masaaki Imaizumi, Takafumi Ono, Ryo Okamoto, and Shigeki Takeuchi.
Consistent Nonparametric Different-Feature Selection via the Sparsest k-Subgraph Problem
arXiv:1707.09688, 2017.

Patents

Satoshi Hara, Takayuki Katsuki, US Patent #9892012, 2018.
Satoshi Hara, Takayuki Katsuki, US Patent Application #20180107574, 2018.
Satoshi Hara, Toshinari Itoko, US Patent Application #20180025036, 2018.
Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa, US Patent Application #20180018574, 2018.
Satoshi Hara, Gakuto Kurata, Shigeru Nakagawa, Seiji Takeda, US Patent Application #20180012124, 2018.
Satoshi Hara, Tetsuro Morimura, Rudy Raymond, US Patent #9626631, 2017.
Satoshi Hara, Takayuki Katsuki, Tetsuro Morimura, Yasunori Yamada, US Patent Application #20170228639, 2017.
Satoshi Hara, Takayuki Katsuki, US Patent Application #20170193380, 2017.
Satoshi Hara, US Patent Application #20170060124, 2017.
Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, US Patent Application #20160327417, 2016.
Satoshi Hara, Tetsuro Morimura, Rudy Raymond, Hidemasa Muta, US Patent Application #20160092782, 2016.
Satoshi Hara, Tetsuro Morimura, Hidemasa Muta, Rudy Raymond, US Patent Application #20150379075, 2015.