谢 明 昆 Ming-Kun Xie Postdoctoral Researcher Imperfect Information Learning Team RIKEN Center for Advanced Intelligence Project Email: ming-kun.xie@riken.jp, mkxie@nuaa.edu.cn

About Me

I am a postdoctoral researcher in the Imperfect Information Learning Team at RIKEN Center for Advanced Intelligence Project, led by professor Masashi Sugiyama. I obtained my Ph.D. degree from Department of Computer Science and Technology in Nanjing University of Aeronautics and Astronautics in June 2024, where I was very fortunate to be advised by professor Sheng-Jun Huang.

My research interests include machine learning and data mining. Recently, I focus on the following topics:

• Robust Multi-Label Learning
  Improving the robustness of MLL under complex environment, including semi-supervised multi-label learning, partial multi-label learning, multi-label learning with noisy labels, and single positive multi-label learning,.
  An Awesome List of Deep Weakly-Supervised Multi-Label Learning!

• Weakly Supervised Learning
  Developing effective learning algorithms for various weakly supervised learning scenarios, including learning with noisy labels, partial label learning, and semi-supervised learning.

Publications

Preprints

• A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation.
  Feng Sun, Ming-Kun Xie and Sheng-Jun Huang
  arXiv:2207.02410, 2022
  [arXiv][GitHub]

Journal

• UNM: A Universal Approach for Noisy Multi-label Learning.
  Jia-Yao Chen, Shao-Yuan Li, Sheng-Jun Huang, Songcan Chen, Lei Wang, Ming-Kun Xie
  In: IEEE Transactions on Knowledge and Data Engineering (TKDE), in press.
  [preprint]

• CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise.
  Ming-Kun Xie and Sheng-Jun Huang
  In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), in press.
  [preprint] [CCMN Code (Linear)][CCMN Code (Deep)]

• Partial Multi-Label Learning with Noisy Label Identification.
  Ming-Kun Xie and Sheng-Jun Huang
  In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
  [preprint][PML-NI Code][MIPML-NI Code]

Conference

• Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL.
  Qin-Wen Luo, Ming-Kun Xie, Ye-Wen Wang, Sheng-Jun Huang
  In: Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'24), 2024.
  

• Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning.
  Jia-Hao Xiao, Ming-Kun Xie, Heng-Bo Fan, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
  In: Proceedings of the 18th European Conference on Computer Vision (ECCV'24), 2024.
  

• Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training.
  Ming-Kun Xie, Jia-Hao Xiao, Pei Peng, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
  In: Proceedings of the 41st International Conference on Machine Learning (ICML'24), 2024.
  [PDF][GitHub]

• Asymmetric Beta Loss for Evidence-Based Safe Semi-Supervised Multi-Label Learning.
  Hao-Zhe Liu, Ming-Kun Xie, Chen-Chen Zong, Sheng-Jun Huang
  In: Proceedings of the 30th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'24), 2024.
  [PDF][GitHub]

• Dirichlet-Based Prediction Calibration for Learning with Noisy Labels.
  Chen-Chen Zong, Ye-Wen Wang, Ming-Kun Xie, Sheng-Jun Huang
  In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI'24), 2024.
  [arXiv][GitHub]

• Unlocking the Power of Open Set: A New Perspective for Open-set Noisy Label Learnin.
  Wenhai Wan, Xinrui Wang, Ming-Kun Xie, Shao-Yuan Li, Sheng-Jun Huang, Songcan Chen
  In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI'24), 2024.
  [arXiv][GitHub]

• Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning.
  Ming-Kun Xie, Jia-Hao Xiao, Hao-Zhe Liu, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
  In: Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS'23), 2023.
  [PDF][GitHub]

• Multi-Label Knowledge Distillation.
  Penghui Yang, Ming-Kun Xie, Chen-Chen Zong, Lei Feng, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
  In: Proceedings of the International Conference on Computer Vision (ICCV'23), 2023.
  [PDF][GitHub]

• Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels.
  Ming-Kun Xie, Jia-Hao Xiao and Sheng-Jun Huang
  In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS'22), 2022.
  [PDF][GitHub]

• Multi-Label Learning with Pairwise Relevance Ordering.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS'21), 2021.
  [PDF]

• Partial Multi-Label Learning with Meta Disambiguation.
  Ming-Kun Xie, Feng Sun, and Sheng-Jun Huang
  In: Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'21), 2021.
  [PDF]

• Semi-Supervised Partial Multi-Label Learning.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 20th IEEE International Conference on Data Mining (ICDM'20), 2020.
  [PDF][Code]

• Partial Multi-Label Learning with Noisy Label Identification.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 34nd AAAI Conference on Artificial Intelligence (AAAI'20), 2020.
  [PDF]

• Learning Class-Conditional GANs with Active Sampling.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'19), 2019.
  [PDF][preprint]

• Active Feature Acquisition with Supervised Matrix Completion
  Sheng-Jun Huang, Miao Xu, Ming-Kun Xie, Masashi Sugiyama, Gang Niu, and Songcan Chen
  In: Proceedings of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'18), 2018.
  [PDF][arXiv]

• Partial Multi-Label Learning.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018.
  [PDF]

Professional Services

• Conference Program Committee Member/Reviewer: NeurIPS'24,23,22, ICML'24,23,22, ICLR'25,24,23, AAAI'25,24,23,22,21, IJCAI'24,23,22,20, CVPR'24,23, ICCV'23, ECCV'24,22, AISTATS'25,23
• Journal Reviewer: IEEE TPAMI, Machine Learning, IEEE TNNLS, IEEE TCSVT, IEEE TMI, SCIENCE CHINA Information Sciences, Pattern Recognition

Honors

• The 1st Learning and Mining with Noisy Labels Challenge at IJCAI Runner-up, 2022
• Baidu Scholarship Finalist, 2021
• Outstanding Graduates of Jiangsu Province, 2021
• National Scholarship, 2020
• Merit Student Award of Jiangsu Province, 2020
• Outstanding Graduates Awards of NUAA, 2018
• Innovation Scholarship of MIIT, 2017
• Student Travel Award: AAAI'18, KDD'19, AAAI'20