Y. Zhe, R. Nagaike, D. Nishiyama, K. Fukuchi, and J. Sakuma.Adversarial Attacks on Hidden Tasks in Multi-Task Learning. arXiv:2405.15244v2 [cs.LG], 2024.
M. Fujikawa, Y. Akimoto, J. Sakuma, and K. Fukuchi.Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. arXiv:2405.16906v1 [stat.ML], 2024.
K. Fukuchi and J. Sakuma.Demographic Parity Constrained Minimax Optimal Regression under Linear Model. arXiv:2206.11546v3 [math.ST], 2023.
A. Miyagi, Y. Miyauchi, A. Maki, K. Fukuchi, J. Sakuma, and Y. Akimoto.Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min--Max Optimization and its Application to Berthing Control Tasks. arXiv:2303.16079v1 [cs.NE], 2023.
T. Tanabe, R. Sato, K. Fukuchi, J. Sakuma, and Y. Akimoto.Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification. arXiv:2211.03413v2 [cs.LG], 2023.
Journal
D. Nishiyama, K. Fukuchi, Y. Akimoto, and J. Sakuma.CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy. IEICE Transactions on Information and Systems, vol. E106-d, 4, pp. 523-537, 2023. doi: 10.1587/transinf.2022EDP7200.
A. Miyagi, K. Fukuchi, J. Sakuma, and Y. Akimoto.Adaptive scenario subset selection for worst-case optimization and its application to well placement optimization. Applied Soft Computing, vol. 133, 109842, pp. 1-19, 2022. doi: 10.1016/j.asoc.2022.109842.
J. Liu, W. Zhang, K. Fukuchi, Y. Akimoto, and J. Sakuma.Unauthorized AI cannot recognize me: Reversible adversarial example. Pattern Recognition, vol. 134, 109048, pp. 1-9, 2022. doi: 10.1016/j.patcog.2022.109048.
T.,Q. Tran, K. Fukuchi, Y. Akimoto, and J. Sakuma.Statistically Significant Pattern Mining with Ordinal Utility. IEEE Transactions on Knowledge ,and, Data Engineering, vol. 35, 9, pp. 8770-8783, 2022. doi: 10.1109/tkde.2022.3208626.
Y. Zhe, K. Fukuchi, Y. Akimoto, and J. Sakuma.Domain Generalization via Adversarially Learned Novel Domains. IEEE Access, vol. 10, pp. 101855-101868, 2022. doi: 10.1109/access.2022.3209815.
K. Fukuchi, C.,M. Yu, and J. Sakuma.Locally Differentially Private Minimum Finding. IEICE Transactions on Information and Systems, vol. E105-d, 8, pp. 1418-1430, 2022. doi: 10.1587/transinf.2021EDP7187.
K. Fukuchi, T. Kamishima, and J. Sakuma.Prediction with Model-Based Neutrality. IEICE Transactions on Information and Systems, vol. E98.d, 8, pp. 1503-1516, 2015. doi: 10.1587/transinf.2014EDP7367.
Conference
K. Fukuchi and J. Sakuma.Demographic Parity Constrained Minimax Optimal Regression under Linear Model. Advances in Neural Information Processing Systems, vol. 36, arXiv:2206.11546v3 [math.ST], pp. 8653-8689, 2023.
K. Xu, K. Fukuchi, Y. Akimoto, and J. Sakuma.Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 519-526, 2023. doi: 10.24963/ijcai.2023/58.
Y. Akimoto, K. Fukuchi, Y. Akimoto, and J. Sakuma.Privformer: Privacy-preserving Transformer with MPC. 2023 IEEE 8th European Symposium on Security and Privacy, pp. 392-410, 2023. doi: 10.1109/EuroSP57164.2023.00031.
K. Kakizaki, K. Fukuchi, and J. Sakuma.Certified Defense for Content Based Image Retrieval. The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4561-4570, 2023.
T. Tanabe, R. Sato, K. Fukuchi, J. Sakuma, and Y. Akimoto.Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification. Advances in Neural Information Processing Systems, vol. 35, pp. 6967–6981, 2022.
A. Miyagi, K. Fukuchi, J. Sakuma, and Y. Akimoto.Black-box min-max continuous optimization using CMA-ES with worst-case ranking approximation. GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 823-831, 2022. doi: 10.1145/3512290.3528702.
D. Nishiyama, K. Fukuchi, Y. Akimoto, and J. Sakuma.CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy. 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2022. doi: 10.1109/ijcnn55064.2022.9892108.
R. Sato, K. Fukuchi, Y. Akimoto, and J. Sakuma.Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning. 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–10, 2022. doi: 10.1109/ijcnn55064.2022.9892464.
H. Syou, K. Fukuchi, Y. Akimoto, and J. Sakuma.Did You Use My GAN to Generate Fake? Post-hoc Attribution of GAN Generated Images via Latent Recovery. 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2022. doi: 10.1109/ijcnn55064.2022.9892704.
Y. Zhe, K. Fukuchi, Y. Akimoto, and J. Sakuma.Domain Generalization via Adversarial Learned Novel Domains. 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6, 2022. doi: 10.1109/icme52920.2022.9860025.
T.,Q. Tran, K. Fukuchi, Y. Akimoto, and J. Sakuma.Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. The Thirty-Sixth AAAI Conference on Artificial Intelligence, vol. 36, 9, pp. 9614-9622, 2022. doi: 10.1609/aaai.v36i9.21195.
A. Miyagi, K. Fukuchi, J. Sakuma, and Y. Akimoto.Adaptive scenario subset selection for min-max black-box continuous optimization. GECCO '21: Genetic and Evolutionary Computation Conference, pp. 697–705, 2021. doi: 10.1145/3449639.3459291.
D. Morinaga, K. Fukuchi, J. Sakuma, and Y. Akimoto.Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions. GECCO '21: Genetic and Evolutionary Computation Conference, arXiv:2103.01578v2 [cs.NE], 2021. doi: 10.1145/3449639.3459289.
T. Tanabe, K. Fukuchi, J. Sakuma, and Y. Akimoto.Level generation for angry birds with sequential VAE and latent variable evolution. GECCO '21: Genetic and Evolutionary Computation Conference, pp. 1052–1060, 2021. doi: 10.1145/3449639.3459290.
T.,Q. Tran, K. Fukuchi, Y. Akimoto, and J. Sakuma.Statistically Significant Pattern Mining with Ordinal Utility. The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1645–1655, 2020. doi: 10.1145/3394486.3403215.
N. Sakamoto, E. Semmatsu, K. Fukuchi, J. Sakuma, and Y. Akimoto.Deep generative model for non-convex constraint handling. GECCO '20: Genetic and Evolutionary Computation Conference, pp. 636–644, 2020. doi: 10.1145/3377930.3390170.
K. Fukuchi, S. Hara, and T. Maehara.Faking Fairness via Stealthily Biased Sampling. AAAI Conference on Artificial Intelligence, vol. 34, pp. 412-419, 2020. doi: 10.1609/aaai.v34i01.5377.
K. Fukuchi and J. Sakuma.Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. 2018 IEEE International Symposium on Information Theory (ISIT), arXiv:1801.05362v1 [cs.IT], pp. 1041-1045, 2018. doi: 10.1109/isit.2018.8437725.
K. Fukuchi, Q.,K. Tran, and J. Sakuma.Differentially Private Empirical Risk Minimization with Input Perturbation. Discovery Science, pp. 82-90, 2017.
K. Kakizaki, K. Fukuchi, and J. Sakuma.Differentially Private Chi-squared Test by Unit Circle Mechanism. The 34th International Conference on Machine Learning, vol. 70, pp. 1761–1770, 2017.
K. Fukuchi and J. Sakuma.Minimax Optimal Estimators for Additive Scalar Functionals of Discrete Distributions. 2017 IEEE International Symposium on Information Theory (ISIT), arXiv:1701.06381v3 [cs.IT], pp. 2103-2107, 2017. doi: 10.1109/ISIT.2017.8006900.
R. Okada, K. Fukuchi, and J. Sakuma.Differentially Private Analysis of Outliers. Machine Learning and Knowledge Discovery in Databases, vol. 9285, pp. 458–473, 2015. doi: 10.1007/978-3-319-23525-7\_28.
K. Fukuchi and J. Sakuma.Neutralized Empirical Risk Minimization with Generalization Neutrality Bound. Machine Learning and Knowledge Discovery in Databases, vol. 8724, pp. 418–433, 2014. doi: 10.1007/978-3-662-44848-9\_27.
K. Fukuchi, J. Sakuma, and T. Kamishima.Prediction with Model-Based Neutrality. Machine Learning and Knowledge Discovery in Databases, vol. 8189, pp. 499–514, 2013. doi: 10.1007/978-3-642-40991-2\_32.
Workshop
K. Fukuchi and J. Sakuma.Minimax Optimal Fair Regression under Linear Model. Algorithmic Fairness through the Lens of Causality and Privacy (at The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022)), 2022.
Awards and Honors
H. Oiso, K. Fukuchi, Y. Akimoto, and J. Sakuma.CSS2023 Student Paper Award. Computer Security Symposium 2023 (CSS2023), 2023.
K. Fukuchi and J. Sakuma.SITA Best Young Researcher Paper Award 2018. The 41th Symposium on Information Theory and its Applications (SITA2019), 2019.
K. Fukuchi and J. Sakuma.Hornable Award of Student Presentation. The 20th Information-Based Induction Sciences Workshop (IBIS), 2017.
K. Fukuchi.IBM Ph.D. Fellowship Award 2015–2016. Ibm, 2016.
K. Kakizaki, K. Fukuchi, and J. Sakuma.CSS2016 Hornable Paper Award. Computer Security Symposium 2016 (CSS2016), 2016.
R. Okada, K. Fukuchi, and J. Sakuma.Best Paper Award. The 7th Forum on Data Engineering and Information Management (DEIM2015), 2015.
Research Funds
K. Fukuchi.Demographi parity制約下における公平な回帰問題におけるMinimax最適性の解明. JSPS KAKENHI Grant Number 20K19750, 2023-2026.
K. Fukuchi.大規模離散分布におけるminimax最適な汎関数推定. JSPS KAKENHI Grant Number 20K19750, 2020-2023.
K. Fukuchi.離散分布におけるスカラー値のMinimax最適な推定量. JSPS KAKENHI Grant Number JP17J0103, 2017-2018.
Invited Talks
福地 一斗.機械学習アルゴリズムに潜む不公平なバイアスとその理論. 2022年電子情報通信学会ソサイエティ大会 AT-1 データサイエンスと情報理論, 2022. In Japanese.
K. Fukuchi.Faking Fairness via Stealthily Biased Sampling. ACML 2019 Workshop on Statistics ,&, Machine Learning Researchers in Japan, 2019.
福地 一斗.公平性を保証したAI/機械学習アルゴリズムの最新理論. 産業技術総合研究所人工知能研究センター 第38回AIセミナー 「機械学習/人工知能の公平性」, 2019. In Japanese.
福地 一斗, 福馬 智生, 永野 雄大.NeurIPS概要・今年の傾向. 第76回人工知能セミナー, 2019. In Japanese.
福地 一斗.頑健性を持った機械学習. 第76回人工知能セミナー, 2019. In Japanese.
福地 一斗.公平性に配慮した学習とその理論的課題. 第21回情報論的学習理論ワークショップ (IBIS 2018), 企画セッション:学習理論, 2018. In Japanese.
福地 一斗.敵対/分配的文脈に対するバンディット学習における結果的公平性. 統計学・機械学習若手シンポジウム「大規模複雑データに対する統計・機械学習のアプローチ」, 2017. In Japanese.
T. Kamishima, K. Fukuchi, J. Sakuma, S. Akaho, and H. Asoh.Future Directions of Fairness-Aware Data Mining: Recommendation, Causality, and Theoretical Aspects. 2nd Workshop on Fairness, Accountability, ,and, Transparency in Machine Learning, 2015.
Preprint (Old)
A. Miyagi, K. Fukuchi, J. Sakuma, and Y. Akimoto.Adaptive Scenario Subset Selection for Worst-Case Optimization and its Application to Well Placement Optimization. arXiv:2211.16574v1 [cs.NE], 2022.
T. Tran, K. Fukuchi, Y. Akimoto, and J. Sakuma.Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. arXiv:2109.04518v1 [cs.LG], 2021.
D. Morinaga, K. Fukuchi, J. Sakuma, and Y. Akimoto.Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions. arXiv:2103.01578v2 [cs.NE], 2021.
T. Tran, K. Fukuchi, Y. Akimoto, and J. Sakuma.Statistically Significant Pattern Mining with Ordinal Utility. arXiv:2008.10747v1 [stat.ME], 2020.
K. Fukuchi, S. Hara, and T. Maehara.Faking Fairness via Stealthily Biased Sampling. arXiv:1901.08291v2 [stat.ML], 2019.
K. Fukuchi, C.,M. Yu, A. Haishima, and J. Sakuma.Locally Differentially Private Minimum Finding. arXiv:1905.11067v1 [math.ST], 2019.
K. Fukuchi and J. Sakuma.Minimax Optimal Additive Functional Estimation with Discrete Distribution. arXiv:1812.00001v1 [cs.IT], 2018.
K. Fukuchi and J. Sakuma.Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. arXiv:1801.05362v1 [cs.IT], 2018.
K. Fukuchi and J. Sakuma.Minimax Optimal Estimators for Additive Scalar Functionals of Discrete Distributions. arXiv:1701.06381v3 [cs.IT], 2017.
K. Fukuchi, Q.,K. Tran, and J. Sakuma.Differentially Private Empirical Risk Minimization with Input Perturbation. arXiv:1710.07425v1 [stat.ML], 2017.
K. Fukuchi and J. Sakuma.Neutralized Empirical Risk Minimization with Generalization Neutrality Bound. arXiv:1511.01987v1 [stat.ML], 2015.
R. Okada, K. Fukuchi, K. Kakizaki, and J. Sakuma.Differentially Private Analysis of Outliers. arXiv:1507.06763v2 [stat.ML], 2015.
K. Fukuchi and J. Sakuma.Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences. arXiv:1506.07721v1 [stat.ML], 2015.