Fairwashing: the risk of rationalization U Aïvodji, H Arai, O Fortineau, S Gambs, S Hara, A Tapp Proceedings of the 36th International Conference on Machine Learning (ICML …, 0 | 153* | |

Making tree ensembles interpretable: A Bayesian model selection approach S Hara, K Hayashi Proceedings of the 21th International Conference on Artificial Intelligence …, 2016 | 129 | 2016 |

Making Tree Ensembles Interpretable S Hara, K Hayashi 2016 Workshop on Human Interpretability in Machine Learning, 81-85, 2016 | 107 | 2016 |

Enumerate lasso solutions for feature selection S Hara, T Maehara Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017 | 63 | 2017 |

Separation of stationary and non-stationary sources with a generalized eigenvalue problem S Hara, Y Kawahara, T Washio, P Von BüNau, T Tokunaga, K Yumoto Neural networks 33, 7-20, 2012 | 63 | 2012 |

Data Cleansing for Models Trained with SGD S Hara, A Nitanda, T Maehara Advances in Neural Information Processing Systems 32 (NeurIPS'19), 2019 | 61 | 2019 |

Quantile regression approach to conditional mode estimation H Ota, K Kato, S Hara | 51 | 2019 |

Learning a common substructure of multiple graphical Gaussian models S Hara, T Washio Neural Networks 38, 23-38, 2012 | 41 | 2012 |

Stationary subspace analysis as a generalized eigenvalue problem S Hara, Y Kawahara, T Washio, P Von Bünau Neural Information Processing. Theory and Algorithms: 17th International …, 2010 | 24 | 2010 |

Anomaly Detection in Reconstructed Quantum States Using a Machine-Learning Technique Satoshi Hara, Takafumi Ono, Ryo Okamoto, Takashi Washio, Shigeki Takeuchi Physical Review A 89 (2), 022104, 2014 | 16 | 2014 |

Faking Fairness via Stealthily Biased Sampling K Fukuchi, S Hara, T Maehara arXiv preprint arXiv:1901.08291, 2019 | 15* | 2019 |

Approximate and exact enumeration of rule models S Hara, M Ishihata Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 15 | 2018 |

A Consistent Method for Graph Based Anomaly Localization Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa ... Proceedings of the Eighteenth International Conference on Artificial …, 2015 | 13* | 2015 |

Discounted average degree density metric and new algorithms for the densest subgraph problem H Yanagisawa, S Hara Networks 71 (1), 3-15, 2018 | 11 | 2018 |

Common substructure learning of multiple graphical gaussian models S Hara, T Washio Machine Learning and Knowledge Discovery in Databases: European Conference …, 2011 | 11 | 2011 |

Finding alternate features in lasso S Hara, T Maehara arXiv preprint arXiv:1611.05940, 2016 | 9 | 2016 |

Maximally invariant data perturbation as explanation S Hara, K Ikeno, T Soma, T Maehara arXiv preprint arXiv:1806.07004, 2018 | 8 | 2018 |

Quantum-state anomaly detection for arbitrary errors using a machine-learning technique S Hara, T Ono, R Okamoto, T Washio, S Takeuchi Physical Review A 94 (4), 042341, 2016 | 8 | 2016 |

Maximizing invariant data perturbation with stochastic optimization K Ikeno, S Hara arXiv preprint arXiv:1807.05077, 2018 | 7 | 2018 |

Consistent and Efficient Nonparametric Different-Feature Selection ST Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa, Takafumi Ono, Ryo Okamoto Proceedings of the 20th International Conference on Artificial Intelligence …, 2017 | 7* | 2017 |