ジャーナル論文 / Journal
- Zhao, T., Li, G., Zhao, T., Chen, Y., Xie, N., Niu, G., and Sugiyama, M., "Learning explainable task-relevant state representation for model-free deep reinforcement learning", Neural Netw. 180, 106741, (2024).
- Zhang, J., Song, B., Wang, H., Han, B., Liu, T., Liu, L., and Sugiyama, M., "BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning", IEEE Trans. Pattern Anal. Machine Intell. PP(99), 1–12, (2024).
- Riou, C., Honda, J., and Sugiyam, M., "The Survival Bandit Problem", Transactions on Machine Learning Rese, 1–66, (2024).
- Luo, W., Chen, S., Liu, T., Han, B., Niu, G., Sugiyama, M., Tao, D., and Gong, C., "Estimating Per-Class Statistics for Label Noise Learning", IEEE Trans. Pattern Anal. Machine Intell. PP(99), 1–17, (2024).
- Hasegawa, N., Sugiyama, M., and Igarashi, K., "Random forest machine-learning algorithm classifies white- and brown-rot fungi according to the number of the genes encoding Carbohydrate-Active enZyme families", Appl. Environ. Microbiol. 90(7), e00482–24, (2024).
- Hasegawa, N., Sugiyama, M., and Igarashi, K., "Acetylxylan esterase is the key to the host specialization of wood-decay fungi predicted by random forest machine-learning algorithm", Journal of Wood Science 70(44), (2024).
- Gao, Y., Wu, D., Zhang, J., Gan, G., Xia, S., Niu, G., and Sugiyam, M., "On the effectiveness of adversarial training against backdoor attacks", IEEE Trans. Neural Netw. Learn. Syst. 35(10), 14878 –14888, (2024).
- Zhao, T., Wu, S., Li, G., Chen, Y., Niu, G., and Sugiyama, M., "Learning Intention-Aware Policies in Deep Reinforcement Learning", Neural Comput. 35(10), 1657–1677, (2023).
- Zhao, T., Wang, Y., Sun, W., Chen, Y., Niu, G., and Sugiyama, M., "Representation learning for continuous action spaces is beneficial for efficient policy learning", Neural Netw. 159, 137–152, (2023).
- Yang, S., Wu, S., Yang, E., Han, B., Liu, Y., Xu, M., Niu, G., and Liu, T., "A Parametrical Model for Instance-Dependent Label Noise", IEEE Trans. Pattern Anal. Machine Intell. 45(12), 14055–14068, (2023).
- Wu, Z., Lyu, J., and Sugiyama, M., "Learning With Proper Partial Labels", Neural Comput. 35(1), 58–81, (2023).
- Sugiyama, M., "IBISML研究会の現状とこれから", IEICE Information and Systems Society Journal 27(4), 8–9, (2023).
- Otsubo, Y., Otani, N., Chikasue, M., Nishino, M., and Sugiyama, M., "Root cause estimation of faults in production processes: a novel approach inspired by approximate Bayesian computation", Int. J. Prod. Res. 61(5), 1556–1574, (2023).
- Osa, T., Osajima, N., Aizawa, M., and Harada, T., "Learning Adaptive Policies for Autonomous Excavation Under Various Soil Conditions by Adversarial Domain Sampling", IEEE Robot. Autom. Lett. 8(9), 5536–5543, (2023).
- Nakajima, S., and Sugiyama, M., "Positive-unlabeled classification under class-prior shift: a prior-invariant approach based on density ratio estimation", Mach. Learn. 112, 889–919, (2023).
- Lv, J., Liu, B., Feng, L., Xu, N., Xu, M., An, B., Niu, G., Geng, X., and Sugiyama, M., "On the Robustness of Average Losses for Partial-Label Learning", IEEE Trans. Pattern Anal. Machine Intell. PP(99), 1–15, (2023).
- Gong, C., Ding, Y., Han, B., Niu, G., Yang, J., You, J. J., Tao, D., and Sugiyama, M., "Class-Wise Denoising for Robust Learning under Label Noise", IEEE Trans. Pattern Anal. Machine Intell. 45(3), 2835–2848, (2023).
- Gao, Y., Wu, D., Zhang, J., Gan, G., Xia, S., Niu, G., and Sugiyama, M., "On the Effectiveness of Adversarial Training Against Backdoor Attacks", IEEE Trans. Neural Netw. Learn. Syst. PP(99), 1–11, (2023).
- Chen, S., Gong, C., Li, X., Yang, J., Niu, G., and Sugiyama, M., "Boundary-restricted metric learning", Mach. Learn. 112(12), 4723–4762, (2023).
- Zhang, J., Xu, X., Han, B., Liu, T., Cui, L., Niu, G., and Sugiyama, M., "NoiLin: Improving adversarial training and correcting stereotype of noisy labels", Transactions on Machine Learning Research, 1–25, (2022).
- Wu, S., Liu, T., Han, B., Yu, J., Niu, G., and Sugiyama, M., "Learning from noisy pairwise similarity and unlabeled data", J. Mach. Learn. Res. 23(307), 1–34, (2022).
- Wang, Z., Jiang, J., Han, B., Feng, L., An, B., Niu, G., and Long, G., "SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning", Transactions on Machine Learning Research, (2022).
- Tanimoto, A., Yamada, S., Takenouchi, T., Sugiyama, M., and Kashima, H., "Improving imbalanced classification using near-miss instances", Expert Syst. Appl. 201(117130), 1–15, (2022).
- Pan, Y., Tsang, I. W., Chen, W., Niu, G., and Sugiyama, M., "Fast and Robust Rank Aggregation against Model Misspecification", J. Mach. Learn. Res. 23(23), 1–35, (2022).
- Osa, T., and Aizawa, M., "Deep Reinforcement Learning with Adversarial Training for Automated Excavation Using Depth Images", IEEE Access 10, 4523–4535, (2022).
- Osa, T., Tangkaratt, V., and Sugiyama, M., "Discovering diverse solutions in deep reinforcement learning by maximizing state–action-based mutual information", Neural Netw. 152, 90–104, (2022).
- Ohnishi, M., Ishikawa, I., Kuroki, Y., and Ikeda, M., "Dynamic Structure Estimation from Bandit Feedback.", CoRR abs/2206.00861, (2022).
- Matsuo, Y., LeCun, Y., Sahani, M., Precup, D., Silver, D., Sugiyama, M., Uchibe, E., and Morimoto, J., "Deep learning, reinforcement learning, and world models", Neural Netw. 152, 267–275, (2022).
- Lu, Z., Xu, C., Du, B., Ishida, T., Zhang, L., and Sugiyama, M., "LocalDrop: A hybrid regularization for deep neural networks", IEEE Trans. Pattern Anal. Machine Intell. 44(7), 3590-–3601, (2022).
- Ishiguro, H., Ishida, T., and Sugiyama, M., "Learning from Noisy Complementary Labels with Robust Loss Functions", IEICE Trans. Inf. Syst. E105-D(2), 364–376, (2022).
- Gong, C., Yang, J., You, J., and Sugiyama, M., "Centroid Estimation With Guaranteed Efficiency: A General Framework for Weakly Supervised Learning", IEEE Trans. Pattern Anal. Machine Intell. 44(6), 2841–2855, (2022).
- Zhang, T., Yamane, I., Lu, N., and Sugiyama, M., "A one-step approach to covariate shift adaptation", SN Computer Science 2(4), (2021).
- Xu, W., Niu, G., Hyvarinen, A., and Sugiyama, M., "Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs", Neural Comput. 33(8), 2128–2162, (2021).
- Xie, Z., He, F., Fu, S., Sato, I., Tao, D., and Sugiyama, M., "Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting", Neural Comput. 33(8), 2163–2192, (2021).
- Ugawa, M., Kawamura, Y., Toda, K., Teranishi, K., Morita, H., Adachi, H., Tamoto, R., Nomaru, H., Nakagawa, K., Sugimoto, K., Borisova, E., An, Y., Konishi, Y., Tabata, S., Morishita, S., Imai, M., Takaku, T., Araki, M., Komatsu, N., Hayashi, Y., Sato, I., Horisaki, R., Noji, H., and Ota, S., "In silico-labeled ghost cytometry", eLife 10, (2021).
- Tsuchiya, T., Charoenphakdee, N., Sato, I., and Sugiyama, M., "Semisupervised Ordinal Regression Based on Empirical Risk Minimization", Neural Comput. 33(12), 3361–3412, (2021).
- Shimada, T., Bao, H., Sato, I., and Sugiyama, M., "Classification From Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization", Neural Comput. 33(5), 1234–1268, (2021).
- Ohnishi, M., Notomista, G., Sugiyama, M., and Egerstedt, M., "Constraint learning for control tasks with limited duration barrier functions", Automatica 127, (2021).
- Fujisawa, M., and Sato, I., "Multilevel Monte Carlo Variational Inference", J. Mach. Learn. Res. 22(278), 1–44, (2021).
国際会議 / Proceedings
- Zhu, H., Soen, A., Cheung, Y. K., and Xie, L., "Online Learning in Betting Markets: Profit versus Prediction", Proceedings of the 41 st International Conference on Machine Learning, (2024).
- Zhang, Z., Han, S., Yao, H., Niu, G., and Sugiyama, M., "Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought", Proceedings of 41st International Conference on Machine Learning (ICML2024) 235, 58967–58983, (2024).
- Yan, K., Cui, S., Wuerkaixi, A., Zhang, J., Han , B., Niu, G., Sugiyama, M., and Zhang, C., "Balancing similarity and complementarity for unimodal and multimodal federated learning", Proceedings of 41st International Conference on Machine Learning (ICML2024) 235, 55739–55758, (2024).
- Xie, M., Xiao, J., Peng, P., Niu, G., Sugiyama, M., and Huang, S., "Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training", Proceedings of 41st International Conference on Machine Learning (ICML2024) 235, 54576–54589, (2024).
- Wuerkaixi, A., Cui, S., Zhang, J., Yan, K., Han, B., Niu, G., Fang , L., Zhang, C., and Sugiyama, M., "Accurate Forgetting for Heterogeneous Federated Continual Learning", Proceedings of Twelfth International Conference on Learning Representations (ICLR2024), 1–19, (2024).
- Wang, W., Ishida, T., Zhan, Y., Niu, G., and Sugiyama, M., "Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical", Proceedings of 41st International Conference on Machine Learning (ICML2024) 235, 50683–50710, (2024).
- Tanaka, Y., Yoshida, S. M., Shibata, T., Terao, M., Okatani, T., and Sugiyama, M., "Appearance-based curriculum for semi-supervised learning with multi-angle unlabeled data", the IEEE Winter Conference on Applications of Computer Vision (WACV2024), 2780–2789, (2024).
- Qian, Y., Zhao, P., Zhang, Y., Sugiyama, M., and Zhou, Z., "Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation", Proceedings of 41st International Conference on Machine Learning (ICML2024) 235, 41383–41415, (2024).
- Omura, M., Osa, T., Mukuta, Y., and Harada, T., "Symmetric Q-Learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning", 38th AAAI Conference on Artificial Intelligence, (2024).
- Nakamura, S., and Sugiyama, M., "Thompson sampling for real-valued combinatorial pure exploration of multi-armed bandit", the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI2024), 14414–14421, (2024).
- Nakamura, S., and Sugiyama, M., "Fixed-budget real-valued combinatorial pure exploration of multi-armed bandit", Proceedings of 27th International Conference on Artificial Intelligence and Statistics (AISTATS2024) 238, 1225–1233, (2024).
- Lee, J., Chiang, C., and Sugiyama, M., "The choice of noninformative priors for Thompson sampling in multiparameter bandit models", the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI2024) 13383(13390), (2024).
- Johannes, ., Osa, T., and Sugiyam, M., "Offline reinforcement learning from datasets with structured non-stationarity", Reinforcement Learning Journal 5, 2140–2161, (2024).
- Fan, Z., Hu, S., Yao, J., Niu, G., Zhang, Y., Sugiyam, M., and Wang, Y., "Locally estimated global perturbations is better than local perturbations for federated sharpness-aware minimization", Proceedings of the 41st International Conference on Machine Learning 235, 12858–12881, (2024).
- Don, Q., Kaneko, T., and Sugiyama, M., "An offline learning of behavior correction policy for vision-based robotic manipulation", Proceedings of 2024 IEEE International Conference on Robotics and Automation (ICRA2024), 5448–5454, (2024).
- Chen, S., Niu, G., Gong, C., Koc, O., Yang, J., and Sugiyama, M., "Robust similarity learning with difference alignment regularization", Proceedings of Twelfth International Conference on Learning Representations (ICLR2024), 1–22, (2024).
- Chen, H., Wang, J., Shah, A., Tao, ., Wei, H., Xie, X., Sugiyama, M., and Raj, B., "Understanding and mitigating the label noise in pre-training on downstream tasks", Proceedings of Twelfth International Conference on Learning Representations (ICLR2024), 1–31, (2024).
- Chen, H., Wang, J., Feng, L., Li, X., Wang, Y., Xie, X., Sugiyam, M., Singh, R., and Raj, B., "A general framework for learning from weak supervision", Proceedings of Machine Learning Research 235, 7462–7485, (2024).
- Braun, G., and Sugiyama, M., "VEC-SBM: Optimal community detection with vectorial edges covariates", Proceedings of 27th International Conference on Artificial Intelligence and Statistics (AISTATS2024) 238, 532–540, (2024).
- Zhu, J., Yu, G., Yao, J., Liu, T., Niu, G., Sugiyama, M., and Han, B., "Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation", Advances in Neural Information Processing Systems 36, 22702–22734, (2023).
- Zhang, Y., and Sugiyama, M., "Online (multinomial) logistic bandit: Improved regret and constant computation cost", Advances in Neural Information Processing Systems 36, 29741–29782, (2023).
- Zhang, Y., and Sugiyama, M., "A Category-theoretical Meta-analysis of Definitions of Disentanglement", Proceedings of Machine Learning Research 202, 41596–41612, (2023).
- Zhang, Y., Zhang, Z., Zhao, P., and Sugiyama, M., "Adapting to continuous covariate shift via online density ratio estimation", Advances in Neural Information Processing Systems 36, 29074–29113, (2023).
- Yang, P., Xie, M., Zong, C., Feng, L., Niu, G., Sugiyama, M., and Huang, S., "Multi-label knowledge distillation", Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV2023), 17271–17280, (2023).
- Xu, X., Zhang, J., Liu, F., Sugiyama, M., and Kankanhalli, M., "Enhancing adversarial contrastive learning via adversarial invariant regularization", Advances in Neural Information Processing Systems 36, 16783–16803, (2023).
- Xu, X., Zhang, J., Liu, F., Sugiyama, M., and Kankanhall, M., "Efficient adversarial contrastive learning via robustness-aware coreset selection", Advances in Neural Information Processing Systems 36, 75798–75825, (2023).
- Xu, J., Chen, S., Ren, Y., Shi, X., Shen, H., Niu, G., and Zhu, X., "Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration.", NeurIPS, (2023).
- Xie, Z., Xu, Z., Zhang, J., Sato, I., and Masashi, S., "On the overlooked pitfalls of weight decay and how to mitigate them: A gradient-norm perspective", Advances in Neural Information Processing Systems 36, 1208–1228, (2023).
- Xie, M., Xiao, J., Liu, H., Niu, G., Sugiyama, M., and Huang, S., "Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning", Advances in Neural Information Processing Systems 36, 25731–25747, (2023).
- Xia, S., Lv, J., Xu, N., Niu, G., and Geng, X., "Towards Effective Visual Representations for Partial-Label Learning", 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 00, 15589–15598, (2023).
- Wei, Z., Feng, L., Han, B., Liu, T., Niu, G., Zhu, X., and Shen, H. T., "A Universal Unbiased Method for Classification from Aggregate Observations.", Icml, 36804–36820, (2023).
- Wei, H., Zhuang, H., Xie, R., Feng, L., Niu, G., An, B., and Li, Y., "Mitigating Memorization of Noisy Labels by Clipping the Model Prediction.", Icml, 36868–36886, (2023).
- Wang, W., Feng, L., Jiang, Y., Niu, G., Zhang, M., and Sugiyama, M., "Binary Classification with Confidence Difference", Advances in Neural Information Processing Systems 36, 5936–5960, (2023).
- Tang, J., Chen, S., Niu, G., Sugiyama, M., and Gong, C., "Distribution Shift Matters for Knowledge Distillation with Webly Collected Images", Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV2023), 17470–17480, (2023).
- Lee, J., Honda, J., and Sugiyama, M., "Thompson exploration with best challenger rule in best arm identification", Proceedings of the 15th Asian Conference on Machine Learning (ACML2023), 646–661, (2023).
- Lee, J., Honda, J., Chiang, C. K., and Sugiyama, M., "Optimality of Thompson sampling with noninformative priors for Pareto bandits", Proceedings of 40th International Conference on Machine Learning (ICML2023), Proceedings of Machine Learning Research 202, 18810–18851, (2023).
- Ishida, T., Yamane, I., Charoenphakdee, N., Niu, G., and Sugiyama, M., "Is the performance of my deep network too good to be true? A direct approach to estimating the Bayes error in binary classification", In Proceedings of Eleventh International Conference on Learning Representations (ICLR2023), (2023).
- Ghamiz, S., Zhang, J., Cordy, M., Papadakis, M., Sugiyama, M., and Traon, L. Y., "GAT: Guided adversarial training with Pareto-optimal auxiliary tasks", Proceedings of 40th International Conference on Machine Learning (ICML2023), Proceedings of Machine Learning Research 202, 11282–11255, (2023).
- Futami, F., and Fujisawa, M., "Time-Independent Information-Theoretic Generalization Bounds for SGLD", Advances in Neural Information Processing Systems 36 (NeurIPS 2023) 36, 8173–8185, (2023).
- Fang, T., Lu, N., Niu, G., and Sugiyama, M., "Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems", Advances in Neural Information Processing Systems 36, 24171–24190, (2023).
- Dong, R., Liu, F., Chi, H., Liu, T., Gong, M., Niu, G., Sugiyama, M., and Han, B., "Diversity-enhancing generative network for few-shot hypothesis adaptation", Proceedings of 40th International Conference on Machine Learning (ICML2023), Proceedings of Machine Learning Research 202, 8260–8275, (2023).
- Cai, X., Zhang, Y., Chiang, C., and Sugiyama, M., "Imitation learning from vague feedback", Advances in Neural Information Processing Systems 36, 48275–48292, (2023).
- Ca, X., Zhang, P., Zhao, L., Bian, J., Sugiyama, M., and Llorens, A., "Distributional Pareto-Optimal Multi-Objective Reinforcement Learning", Advances in Neural Information Processing Systems 36, 15593–15613, (2023).
- Ca, X. Q., Ding, Y. X., Chen, Z. X., Jiang, Y., Sugiyama, M., and Zhou, Z. H., "Seeing differently, acting similarly: Heterogeneously observable imitation learning", Proceedings of Eleventh International Conference on Learning Representations (ICLR2023), (2023).
- Zhu, J., Yao, J., Han, B., Zhang, J., Liu, T., Niu, G., Zhou, J., Xu, J., and Yang, H., "Reliable Adversarial Distillation with Unreliable Teachers", Proceedings of 10th International Conference on Learning Representations (ICLR 2022), (2022).
- Zhou, J., Zhou, J., Zhang, J., Liu, T., Niu, G., Han, B., and Sugiyama, M., "Adversarial training with complementary labels: On the benefit of gradually informative attacks", Advances in Neural Information Processing Systems, 23621–23633, (2022).
- Zhang, Y., Gong, M., Liu, T., Niu, G., Tian, X., Han, B., Schölkopf, B., and Zhang, K., "CausalAdv: Adversarial Robustness Through the Lens of Causality", Proceedings of 10th International Conference on Learning Representations (ICLR 2022), (2022).
- Zhang, F., Feng, L., Han, B., Liu, T., Niu, G., Qin, T., and Sugiyama, M., "Exploiting Class Activation Value for Partial-Label Learning", Proceedings of Tenth International Conference on Learning Representations (ICLR2022), 1–17, (2022).
- Yao, Y., Liu, T., Han, B., Gong, M., Niu, G., Sugiyama, M., and Tao, D., "Rethinking class-prior estimation for positive-unlabeled learning", Proceedings of Tenth International Conference on Learning Representations (ICLR2022), 1–12, (2022).
- Yang, S., Yang, E., Han, B., Liu, Y., Xu, M., Niu, G., and Liu, T., "Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network", Proceedings of 39th International Conference on Machine Learning (ICML 2022), (2022).
- Yan, H., Zhang, J., Feng, J., Sugiyama, M., and Tan, V. Y., "Towards Adversarially Robust Deep Image Denoising", Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22), 1516–1522, (2022).
- Xu, X., Zhang, J., Liu, F., Sugiyama, M., and Kankanhalli, M., "Adversarial attacks and defenses for non-parametric two-sample tests", Proceedings of Machine Learning Research 24743(24769), (2022).
- Xu, N., Qiao, C., Lyu, J., Geng, X., and Zhangg, M., "One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement", Advances in Neural Information Processing Systems 35 (NeurIPS 2022), (2022).
- Xie, Z., Wang, X., Zhang, H., Sato, I., and Sugiyama, M., "Adaptive inertia: Disentangling the effects of adaptive learning rate and momentum", Proceedings of Machine Learning Research, 24430–24459, (2022).
- Xia, X., Liu, T., Han, B., Gong, M., Yu, J., Niu, G., and Sugiyama, M., "Sample selection with uncertainty of losses for learning with noisy labels", Proceedings of Tenth International Conference on Learning Representations (ICLR2022), (2022).
- Xia, S., Lv, J., Xu, N., and Geng, X., "Ambiguity-Induced Contrastive Learning for Instance-Dependent Partial Label Learning", Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 3615–3621, (2022).
- Wei, J., Zhu, Z., Cheng, H., Liu, T., Niu, G., and Liu, Y., "Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations", Proceedings of 10th International Conference on Learning Representations (ICLR 2022), (2022).
- Wei, J., Liu, H., Liu, T., Niu, G., Sugiyama, M., and Liu, Y., "To smooth or not? When label smoothing meets noisy labels", Proceedings of Machine Learning Research 162, 23589–23614, (2022).
- Wang, H., Xiao, R., Li, Y., Feng, L., Niu, G., Chen, G., and Zhao, J., "PiCO: Contrastive Label Disambiguation for Partial Label Learning", Proceedings of 10th International Conference on Learning Representations (ICLR 2022), (2022).
- Tang, Y., Lu, N., Zhang, T., and Sugiyama, M., "Multi-class classification from multiple unlabeled datasets with partial risk regularization", Proceedings of Machine Learning Research, 1–16, (2022).
- Sugiyama, M., Liu, T., Han, B., Liu, Y., and Niu, G., "Learning and mining with noisy labels", Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM2022), 5152–5155, (2022).
- Nakamura, S., Bao, H., and Sugiyama, M., "Robust computation of optimal transport by β-potential regularization", Proceedings of Machine Learning Research, 1–26, (2022).
- Lu, N., Wang, Z., Li, X., Niu, G., Dou, Q., and Sugiyama, M., "Federated learning from only unlabeled data with class-conditional-sharing clients", Proceedings of Tenth International Conference on Learning Representations (ICLR2022), 1–22, (2022).
- Gao, R., Wang, J., Zhou, K., Liu, F., Xie, B., Niu, G., Han, B., and Cheng, J., "Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack", Proceedings of 39th International Conference on Machine Learning (ICML 2022), (2022).
- Cui, S., Zhang, J., Liang, J., Han, B., Sugiyama, M., and Zhang, C., "Synergy-of-experts: Collaborate to improve adversarial robustness", Advances in Neural Information Processing Systems, 32552–32567, (2022).
- Chi, H., Liu, F., Yang, W., Lan, L., Liu, T., Niu, G., and Han, B., "Meta discovery: Learning to discover novel classes given very limited data", Proceedings of Tenth International Conference on Learning Representations (ICLR2022), 25–29, (2022).
- Cheng, D., Liu, T., Ning, Y., Wang, N., Han, B., Niu, G., Gao, X., and Sugiyama, M., "Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation", Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022), 16630–16639, (2022).
- Chen, S., Gong, C., Li, J., Yang, J., Niu, G., and Sugiyama, M., "Learning contrastive embedding in low-dimensional space", Advances in Neural Information Processing Systems, 6345–6357, (2022).
- Cao, Y., Cai, T., Feng, L., Gu, L., GU, ., An, B., Niu, G., and Sugiyama, M., "Generalizing consistent multi-class classification with rejection to be compatible with arbitrary losses", Advances in Neural Information Processing Systems, 521–534, (2022).
- Bao, H., Shimada, T., Xu, L., Sato, I., and Sugiyama, M., "Pairwise Supervision Can Provably Elicit a Decision Boundary", Proceedings of 25th International Conference on Artificial Intelligence and Statistics (AISTATS2022), 2618–2640, (2022).
- Bai, Y., Zhang, Y., Zhao, P., Sugiyama, M., and Zhou, Z., "Adapting to online label shift with provable guarantees", Advances in Neural Information Processing Systems, 29960–29974, (2022).
- Zhang, Y., Niu, G., and Sugiyama, M., "Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization", Proceedings of Machine Learning Research 139, 12501–12512, (2021).
- Zhang, J., Zhu, J., Niu, G., Han, B., Sugiyama, M., and Kankanhalli, M., "Geometry-aware instance-reweighted adversarial training", Proceedings of Ninth International Conference on Learning Representations (ICLR2021), (2021).
- Zhang, J., Xu, C., Li, J., Chen, W., Wang, Y., Tai, Y., Chen, S., Wang, C., Huang, F., and Liu, Y., "Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model", Advance in Neural Information Processing System, (2021).
- Yoshida, S. M., Takenouchi, T., and Sugiyama, M., "Lower-Bounded Proper Losses for Weakly Supervised Classification", Proceedings of Machine Learning Research 139, 12110–12120, (2021).
- Yao, Y., Liu, T., Gong, M., Han, B., Niu, G., and Zhang, K., "Instance-dependent Label-noise Learning under a Structural Causal Model.", NeurIPS, (2021).
- Yan, H., Zhang, J., Niu, G., Feng, J., Tan, V. Y., and Sugiyama, M., "CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection", Proceedings of Machine Learning Research 139, 11693–11703, (2021).
- Yamane, I., Honda, J., Yger, F., and Sugiyama, M., "Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences", Proceedings of Machine Learning Research 139, 11637–11647, (2021).
- Xie, Z., Yuan, L., Zhu, Z., and Sugiyama, M., "Positive-negative momentum: Manipulating stochastic gradient noise to improve generalization", Proceedings of Machine Learning Research 139, 11448–11458, (2021).
- Xie, Z., Sato, I., and Sugiyama, M., "A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima", Proceedings of Ninth International Conference on Learning Representations (ICLR2021), (2021).
- Wu, S., Xia, X., Liu, T., Han, B., Gong, M., Wang, N., Liu, H., and Niu, G., "Class2Simi - A Noise Reduction Perspective on Learning with Noisy Labels.", Icml, 11285–11295, (2021).
- Wang, Q., Liu, F., Han, B., Liu, T., Gong, C., Niu, G., Zhou, M., and Sugiyama, M., "Probabilistic margins for instance reweighting in adversarial training", Advances in Neural Information Processing Systems 34 (NeurIPS 2021), (2021).
- Teshima, T., and Sugiyama, M., "Incorporating causal graphical prior knowledge into predictive modeling via simple data augmentation", Proceedings of Machine Learning Research 161, 86–89, (2021).
- Tao, G., Ji, X., Wang, W., Shuo, C., Lin, C., Cao, Y., Lu, T., Luo, D., and Tai, Y., "Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution", Advance in Neural Information Processing System, (2021).
- Tangkaratt, V., Charoenphakdee, N., and Sugiyama, M., "Robust imitation learning from noisy demonstrations", Proceedings of Machine Learning Research 130, 298–306, (2021).
- Parmas, P., and Sugiyama, M., "A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme", Proceedings of Machine Learning Research 130, 4078–4086, (2021).
- Nozawa, K., and Sato, I., "Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning", Conference on Neural Information Processing Systems, (2021).
- Lu, N., Lei, S., Niu, G., Sato, I., and Sugiyama, M., "Binary Classification from multiple unlabeled datasets via surrogate set classification", Proceedings of Machine Learning Research 139, 7134–7144, (2021).
- Li, X., Liu, T., Han, B., Niu, G., and Sugiyama, M., "Provably end-to-end label-noise learning without anchor points", Proceedings of Machine Learning Research 139, 6403–6413, (2021).
- Li, D., Qiu, T., Chen, S., Li, Q., and Xu, S., "Can We Leverage Predictive Uncertainty to Detect Dataset Shift and Adversarial Examples in Android Malware Detection", Annual Computer Security Applications Conference, (2021).
- Jacovi, A., Niu, G., Goldberg, Y., Sugiyama, M., and , "Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning", Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL2021), 581–592, (2021).
- Han, Z., Fu, Z., Chen, S., and Yang, J., "Contrastive Embedding for Generalized Zero-shot Learning", IEEE Conference on Computer Vision and Pattern Recognition, (2021).
- Gao, R., Liu, F., Zhang, J., Han, B., Liu, T., Niu, G., and Sugiyama, M., "Maximum mean discrepancy is aware of adversarial attacks", Proceedings of Machine Learning Research 139, 3564–3575, (2021).
- Futami, F., Iwata, T., Ueda, N., Sato, I., and Sugiyama, M., "Loss function based second-order Jensen inequality and its application to particle variational inference", Advances in Neural Information Processing Systems 34, 6803–6815, (2021).
- Fujisawa, M., Teshima, T., Sato, I., and Sugiyama, M., "γ-ABC: Outlier-robust approximate Bayesian computation based on a robust divergence estimator", Proceedings of Machine Learning Research 130, 1783–1791, (2021).
- Feng, L., Shu, S., Lu, N., Han, B., Xu, M., Niu, G., An, B., and Sugiyama, M., "Pointwise binary classification with pairwise confidence comparisons", Proceedings of Machine Learning Research 139, 3252–3262, (2021).
- Feng, L., Shu, S., Cao, Y., Tao, L., Wei, H., Xiang, T., An, B., and Niu, G., "Multiple-Instance Learning from Similar and Dissimilar Bags.", Kdd, 374–382, (2021).
- Du, X., Zhang, J., Han, B., Liu, T., Rong, Y., Niu, G., Huang, J., and Sugiyama, M., "Learning diverse-structured networks for adversarial robustness", Proceedings of Machine Learning Research 139, 2880–2891, (2021).
- Dan, S., Bao, H., and Sugiyama, M., "Learning from noisy similar and dissimilar data", Lecture Notes in Comput. Sci. 12976, 233–249, (2021).
- Chen, S., Niu, G., Gong, C., Li, J., Yang, J., and Sugiyama, M., "Large-margin contrastive learning with distance polarization regularizer", Proceedings of Machine Learning Research 139, 1673–1683, (2021).
- Charoenphakdee, N., Vongkulbhisal, J., Chairatanakul, N., and Sugiyama, M., "On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective", Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2021), 5202–5211, (2021).
- Charoenphakdee, N., Cui, Z., Zhang, Y., and Sugiyma, M., "Classification with rejection based on cost-sensitive classification", Proceedings of Machine Learning Research 139, 1507–1517, (2021).
- Cao, Y., Feng, L., Xu, Y., An, B., Niu, G., and Sugiyama, M., "Learning from Similarity-Confidence Data", Proceedings of Machine Learning Research 139, 1272–1282, (2021).
- Berthon, A., Han, B., Liu, T., Niu, G., and Sugiyama, M., "Confidence scores make instance-dependent label-noise learning possible", Proceedings of Machine Learning Research 139, 825–836, (2021).
- Bao, H., and Sugiyama, M., "Fenchel-Young losses with skewed entropies for class-posterior probability estimation", Proceedings of Machine Learning Research 130, 1648–1656, (2021).
- Bai, Y., Yang, E., Han, B., Yang, Y., Li, J., Mao, Y., Niu, G., and Liu, T., "Understanding and Improving Early Stopping for Learning with Noisy Labels.", NeurIPS, (2021).
レビュー / Review
- Kuroki, Y., Honda, J., and Sugiyama, M., "Combinatorial pure exploration with full-bandit feedback and beyond: Solving combinatorial optimization under uncertainty with limited observation", The Fields Institute Communications Series on Data Science and Optimization, (2023).
- Charoenphakdee, N., Lee, J., and Sugiyama, M., "A symmetric loss perspective of reliable machine learning", The Fields Institute Communications Series on Data Science and Optimization, (2023).
- Lu, N., Zhang, T., Fang, T., Teshima, T., and Sugiyama, M., "Rethinking importance weighting for transfer learning", Federated and Transfer Learning 27, 185–231, (2022).
その他 / Other
- Koshizuka, T., Fujisawa, M., Tanaka, Y., and Sato, I., "Initialization Bias of Fourier Neural Operator: Revisiting the Edge of Chaos", arXiv, (2023).