Sheng-Jun Huang

Professor

College of Computer Science and Technology

Nanjing University of Aeronautics and Astronautics

29 Jiangjun Road, Nanjing 211106, P.R.China
Office: Room 234, Computer Science & Technology Building
Email: huangsj@nuaa.edu.cn or huangsj.gm@gmail.com

[Publications]  [Honors]  [Professional Service]  [Teaching]  [Students]  [中文简历]

---

I am a professor in the College of Computer Science and Technology at Nanjing University of Aeronautics and Astronautics. I received my B.Sc. and Ph.D. degrees in computer science from Nanjing University in 2008 and 2014, respectively, under the supervision of Prof. Zhi-Hua Zhou. I was a member of LAMDA Group from 2008 to 2014, and visited Baidu in 2012 for a half year. My research interests include machine learning and data mining. Specifically I am working on active learning and multi-label learning.

News:

• I am invited to give an Early Career Spotlight Talk at IJCAI 2022. [link]
• We won the second place in the 1st Learning and Mining with Noisy Labels Challenge at IJCAI 2022. [link]
• The 19th China Symposium on Machine Learning and Applications (MLA 2021) will be held at NUAA. [homepage]
• We have released a toolbox ALiPy: Active Learning in Python. [homepage] [github]
• We organized an international workshop on active learning at PRICAI 2018. [homepage]

Publications   [Book Chapter]  [Journal Article]  [Conference Paper]
Book Chapter

• 黄圣君. 主动学习研究简介. 见：机器学习及其应用, 2019.


• 黄圣君. 主动学习. 见：中国机器学习白皮书, 2015.

Journal Article

• Robust AUC maximization for classification with pairwise confidence comparisons.
  Haochen Shi, Mingkun Xie, Sheng-Jun Huang
  In: Frontiers of Computer Science (FCS), in press.


• A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation.
  Feng Sun, Ming-Kun Xie, Sheng-Jun Huang
  In: Machine Intelligence Research, in press.


• Robust learning method by reweighting examples with negative learning.
  Boshi Zou, Ming Yang, Chenchen Zong, Mingkun Xie, Sheng-Jun Huang
  In: Journal of Computer Applications, in press.


• 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.


• Robust AUC maximization for classification with pairwise confidence comparisons.
  Haochen Shi, Mingkun Xie and Sheng-Jun Huang
  In: Frontiers of Computer Science (FCS), in press.


• MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection.
  Dong Liang, Jing-Wei Zhang, Ying-Peng Tang and Sheng-Jun Huang
  In: IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2023.


• 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), 2022.


• Learning from Crowds with Sparse and Imbalanced Annotations.
  Ye Shi, Shao-Yuan Li and Sheng-Jun Huang
  In: Machine Learning (MLJ), 2022.


• Improving Deep Label Noise Learning with Dual Active Label Correction.
  Shao-Yuan Li, Ye Shi, Sheng-Jun Huang, and Songcan Chen
  In: Machine Learning (MLJ), 2022.


• Deep Generative Crowdsourcing Learning with Worker Correlation Utilization.
  Shao-Yuan Li , Meng-Long Wei and Sheng-Jun Huang
  In: Ruan Jian Xue Bao/Journal of Software (JOS), 2021.


• 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.


• Recent Advances in Open Set Recognition: A Survey.
  Chuanxin Geng, Sheng-Jun Huang and Songcan Chen
  In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.


• QBox: Partial Transfer Learning with Active Querying for Object Detection.
  Ying-Peng Tang, Xiu-Shen Wei, Bo-Rui Zhao and Sheng-Jun Huang
  In: IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021.


• Visual-guided attentive attributes embedding for zero-shot learning.
  Rui Zhang, Qi Zhu, Xiangyu Xu, Daoqiang Zhang and Sheng-Jun Huang
  In: Neural Networks, 2021.


• Crowdsourcing Aggregation with Deep Bayesian Learning.
  Shao-Yuan Li, Sheng-Jun Huang and Songcan Chen
  In: Science China Information Sciences (SCIS), 2021.


• Incremental Multi-Label Learning with Active Queries.
  Sheng-Jun Huang, Guo-Xiang Li, Wen-Yu Huang and Shao-Yuan Li
  In: Journal of Computer Science and Technology (JCST), 2020.


• LGSLRR: Towards Fusing Discriminative Ordinal Local and Global Structured Low-Rank Representation for Image Recognition.
  Qi Zhu, Rui Zhang, Sheng-Jun Huang, Zheng Zhang and Daoqiang Zhang
  In: Information Sciences, 2020.


• Fast multi-instance multi-label learning.
  Sheng-Jun Huang, Wei Gao and Zhi-Hua Zhou
  In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.


• Label Distribution Learning with Label Correlations on Local Samples.
  Xiuyi Jia, Zechao Li, Xiang Zheng, Weiwei Li and Sheng-Jun Huang
  In: IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019.


• Querying Representative and Informative Super-pixels for Filament Segmentation in Bioimages.
  Wei Shao, Sheng-Jun Huang, Mingxia Liu and Daoqiang Zhang
  In: IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), 2019.


• Cross modal similarity learning with active queries.
  Nengneng Gao, Sheng-Jun Huang, Yi-Fan Yan and Songcan Chen
  In: Pattern Recognition (PR), 2018.


• Joint estimation of multiple conditional gaussian graphical models.
  Feihu Huang, Songcan Chen and Sheng-Jun Huang
  In: IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017.


• WoCE: a framework for clustering ensemble by exploiting the wisdom of crowds theory.
  Yousefnezhad Muhammad, Sheng-Jun Huang, and Daoqiang Zhang
  In: IEEE Transactions on Cybernetics (TCYB), 2017.


• Multi-label active learning by model guided distribution matching.
  Nengneng Gao, Sheng-Jun Huang and Songcan Chen
  In: Frontiers of Computer Science (FCS), 2016.


• Active learning by querying informative and representative examples.
  Sheng-Jun Huang, Rong Jin and Zhi-Hua Zhou
  In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.


• Genome-wide protein function prediction through multi-instance multi-label learning.
  Jian-Sheng Wu, Sheng-Jun Huang and Zhi-Hua Zhou
  In: ACM/IEEE Transactions on Computational Biology and Bioinformatics (TCBB), 2014.


• Multi-instance multi-label learning.
  Zhi-Hua Zhou, Min-Ling Zhang, Sheng-Jun Huang and Yu-Feng Li
  In: Artificial Intelligence (AIJ), 2012.

Conference Paper

• 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 AAAI conference on artificial intelligence (AAAI'24), 2024.


• Unlocking the power of open set: A new perspective for open-set noisy label learning.
  Wenhai Wan, Xinrui Wang, Ming-Kun Xie, Shao-Yuan Li, Sheng-Jun Huang, Songcan Chen
  In: Proceedings of the AAAI conference on artificial intelligence (AAAI'24), 2024.


• Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning.
  Ming-Kun Xie, Jiahao Xiao, Hao-Zhe Liu, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
  In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS'24), 2024.


• One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models.
  Sheng-Jun Huang, Yi Li, Yiming Sun and Ying-Peng Tang
  In: Proceedings of the 12th International Conference on Learning Representations (ICLR'24), 2024.


• Implicit stochastic gradient descent for training physics-informed neural networks.
  Ye Li, Song-Can Chen, Sheng-Jun Huang
  In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'23), 2023.


• Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery.
  Yuyan Zhou, Dong Liang, Songcan Chen, Sheng-Jun Huang, Shuo Yang, Chongyi Li
  In: Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR'23), 2023.


• Multi-Label Knowledge Distillation.
  Penghui Yang, Ming-Kun Xie, Chen-Chen Zong, Lei Feng, Gang Niu, Masashi Sugiyam and Sheng-Jun Huang
  In: Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR'23), 2023.


• A Tailored Physics-informed Neural Network Method for Solving Singularly Perturbed Differential Equations.
  Yiwen Pang, Ye Li and Sheng-Jun Huang
  In: Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence, 2022.


• Active Learning for Multiple Target Models.
  Ying-Peng Tang and Sheng-Jun Huang
  In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS'22), 2022.


• 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.


• Can Adversarial Training Be Manipulated By Non-Robust Features?
  Lue Tao, Lei Feng, Hongxin Wei, Jinfeng Yi, Sheng-Jun Huang and Songcan Chen
  In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS'22), 2022.


• Active Learning for Open-set Annotation.
  Kun-Peng Ning, Xun Zhao, Yu Li and Sheng-Jun Huang
  In: Proceedings of the 33rd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'22), 2022.


• 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.


• Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training.
  Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang and Songcan Chen
  In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS'21), 2021.


• Partial Multi-Label Learning with Meta Disambiguation.
  Ming-Kun Xie, Feng Sun and Sheng-Jun Huang
  In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'21), 2021.


• Dual Active Learning for Both Model and Data Selection.
  Ying-Peng Tang and Sheng-Jun Huang
  In: Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), 2021.


• Asynchronous Active Learning with Distributed Label Querying.
  Sheng-Jun Huang, Chen-Chen Zong, Kun-Peng Ning and Hai-Bo Ye
  In: Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), 2021.


• Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries.
  Kun-Peng Ning, Lue Tao, SongcanChen and Sheng-Jun Huang
  In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI'21), 2021.


• 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.


• Cost-effectively Identifying Causal Effect When Only Response Variable Observable.
  Tian-Zuo Wang, Xi-Zhu Wu, Sheng-Jun Huang and Zhi-Hua Zhou
  In: Proceedings of the 37th International Conference on Machine Learning (ICML'20), 2020.


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


• Uncertainty Aware Graph Gaussian Process for Semi-Supervised Learning.
  Zhao-Yang Liu, Shao-Yuan Li, Songcan Chen, Yao Hu and Sheng-Jun Huang
  In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI'20), 2020.


• Active Learning with Query Generation for Cost-Effective Text Classification.
  Yi-Fan Yan, Sheng-Jun Huang, Jin Xu, Meng Liao, and Shaoyi Chen
  In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI'20), 2020.


• Learning Class-Conditional GANs with Active Sampling.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'19), 2019.


• Multi-View Active Learning for Video Recommendation.
  Jia-Jia Cai, Jun Tang, Qing-Guo Chen, Yao Hu, Xiaobo Wang and Sheng-Jun Huang
  In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19), 2019.


• Towards identifying causal relation between instances and labels.
  Tian-Zuo Wang, Sheng-Jun Huang and Zhi-Hua Zhou
  In: Proceedings of the SIAM International Conference on Data Mining (SDM'19), 2019.


• Self-paced active learning: query the right thing at the right time.
  Ying-Peng Tang and Sheng-Jun Huang
  In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), 2019.


• Active sampling for open-set classification without initial labeled data.
  Zhao-Yang Liu and Sheng-Jun Huang
  In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), 2019.


• Cost-Effective training of deep CNNs with active model adaptation.
  Sheng-Jun Huang, Jia-Wei Zhao and Zhao-Yang Liu
  In: Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'18), 2018.


• 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 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'18), 2018.


• Cost-effective active learning for hierarchical multi-label classification.
  Yi-Fan Yan and Sheng-Jun Huang
  In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI'18), 2018.


• Partial multi-label learning.
  Ming-Kun Xie and Sheng-Jun Huang
  In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018.


• Dual set multi-label learning.
  Chong Liu, Peng Zhao, Sheng-Jun Huang, Yuan Jiang and Zhi-Hua Zhou
  In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018.


• Multi-instance multi-label active learning.
  Sheng-Jun Huang, Nengneng Gao and Songcan Chen
  In: Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'17), 2017.


• Cost-Effective Active Learning from Diverse Labelers.
  Sheng-Jun Huang Jia-Lve Chen, Xin Mu and Zhi-Hua Zhou
  In: Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'17), 2017.


• Margin Distribution Logistic Machine.
  Yi Ding, Sheng-Jun Huang, Chen Zu and Daoqiang Zhang
  In: Proceedings of the 17th SIAM International Conference on Data Mining (SDM'17), 2017.


• Transfer learning with active queries from source domain.
  Sheng-Jun Huang and Songcan Chen
  In: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI'16), 2016.


• Multi-label active learning: query type matters.
  Sheng-Jun Huang, Songcan Chen and Zhi-Hua Zhou
  In: Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI'15), 2015.


• Fast multi-instance multi-label learning.
  Sheng-Jun Huang Wei Gao and Zhi-Hua Zhou.
  In: Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI'14), 2014.


• Active query driven by uncertainty and diversity for incremental multi-label learning.
  Sheng-Jun Huang and Zhi-Hua Zhou.
  In: Proceedings of the 13th IEEE International Conference on Data Mining (ICDM'13), 2013.


• Multi-label hypothesis reuse.
  Sheng-Jun Huang, Yang Yu and Zhi-Hua Zhou.
  In: Proceedings of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'12), 2012.
  (Best Poster Award, oral+poster presentation)


• Multi-label learning by exploiting label correlations locally.
  Sheng-Jun Huang and Zhi-Hua Zhou.
  In: Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI'12), 2012.


• Active learning by querying informative and representative examples.
  Sheng-Jun Huang, Rong Jin and Zhi-Hua Zhou.
  In: Advances in Neural Information Processing Systems 24 (NIPS'10), 2010.

Honors

• AAAI Outstanding PC Award, 2019
• Changkong Scholar of NUAA, 2017
• Young Elite Scientists Sponsorship Program by China Association for Science and Technology, 2016
• CCF Outstanding Doctoral Dissertation Award, 2015
• Excellence Award of CCF-Tencent Open Research Fund, 2015
• Outstanding Doctoral Dissertation Award of Jiangsu Computer Society, 2015
• KDD'12 Best Poster Award (oral+poster presentation), 2012
• Microsoft Fellowship Award, 2011
• CCDM'11 Best Student Paper Award, 2011

Professional Service

• Program Chair: MLA 2021.
• Young Associate Editor: Frontiers of Computer Science.
• Organization Co-Chair: IJCNN'16 Special Session on MLILD, MLA'15, MLA'16
• Publicity Chair: PRICAI'18.
• Publication Chair: ACML'18, PAKDD'19.
• Senior Program Committee: PAKDD'18, AAAI'18, IJCAI'17, ACML'17.
• Program Committee: NIPS'18, KDD'18, IJCAI'18, NIPS'17, KDD'17, AAAI'17, SDM'17, NIPS'16, KDD'16, IJCAI'16, AAAI'16, KDD'15, IJCAI'15, PAKDD'15, etc.
• Journal Reviwer: TPAMI, TKDE, TKDD, MLJ, TNNLS, TCYB, TIST, JCST, PR, etc.
• Web Chair: ACML 2011.

Teaching

• Data Mining (for undergraduate students), Spring, 2015, 2016, 2017, 2018
• Machine Learning (for undergraduate students), Spring, 2021
• Machine Learning (for graduate students, in English), Fall, 2015, 2016, 2017, 2018, 2019
• Introduction to Computational Thinking (for undergraduate students), Fall, 2014, 2015