I received my Ph.D. in 2015 and became an associate professor in 2017, both at Chinese Academy of Sciences (CAS). Before joining Momenta, I worked at Huawei Noah’s Ark Lab and HAOMO.AI. To build practical theory for real machine intelligence, our recent work focuses on data-driven planning & reasoning for autonomous vehicles.

• 12/2021:   I will serve as reviewer/PC for ICML 2022

• 08/2021:   I will serve as SPC (Meta-reviewer) for AAAI 2022

• 07/2021:   We are recruiting full/part time ML/CV researcher/engineer

• 06/2021:   I will serve as reviewer for ICLR 2022

• 06/2021:   I am serving as reviewer for NeurIPS 2021

• 03/2021:   I served as reviewer for ICML 2021

• 11/2020:   Our paper on "Doubly Semisupervised Multimodal Learning" got accepted to Information Fusion

• 10/2020:   I served as a PC member for AAAI 2021

• 09/2020:   Our paper on "Structured Neural Decoding" got accepted to TNNLS

• 06/2020:   I served as a PC member for NeurIPS 2020

• 04/2020:   Our paper on "Item Tagging and Tag-based Recommender" got accepted to SIGIR'20

• 02/2020:   I served as a PC member for IJCAI'20

• 11/2019:   Our paper on "Conditional Generative Neural Decoding" got accepted to AAAI'20

• 10/2019:   Our paper on "Online Bayesian Multi-view Learning" got accepted to Machine Learning

• 09/2019:   I served as a PC member for AAAI'20

• 07/2019:   Our paper won ICME'19 Best Paper Award Runner-Up

• 05/2019:   I was invited to review many AI/ML project proposals for NSFC

• Fields: Machine learning, Bayesian analysis, Semisupervised learning, Multi-view/modal learning, Cross-modal/domain learning, Adversarial/reinforced learning, Multitask/transfer/meta learning, Online learning, Multi-/Partial label learning, Contrastive learning, Distributed data mining

• Models: Latent variable models, Deep generative models, Variational autoencoders, Generative adversarial nets, Normalizing flow, Probabilistic graphical models, Markov random fields, Topic models, Dirichlet process mixtures, Hierarchical Dirichlet processes, Gaussian processes, CNNs, RNNs, GCNs

• Techniques: Approximate Bayesian inference, Variational methods, Expectation maximization, MCMC and Gibbs sampling, Posterior regularization, Stochastic back-propagation, Max-margin and kernel methods, Map/Reduce, Matrix/tensor factorization, Bayesian dropout/pruning

• Applications: Multimedia analysis, Computer vision, Autonomous driving, Recommender systems, Image/text retrieval, Natural language processing, Human-Machine interaction, Neural decoding, Text generation

• Changde Du, Changying Du and Huiguang He. Multimodal Deep Generative Adversarial Models for Scalable Doubly Semi-supervised Learning. Information Fusion, 2020.   (Information Fusion, IF=13.669)
  

• Changde Du, Changying Du, Lijie Huang, Haibao Wang and Huiguang He. Structured Neural Decoding with Multi-task Transfer Learning of Deep Neural Network Representations. IEEE Transactions on Neural Networks and Learning Systems, 2020.   (TNNLS, IF=8.793)
  

• Xu Chen, Changying Du, Xiuqiang He and Jun Wang. A Joint Framework for Item Tagging and Tag-based Recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi'an, China, July 25-30, 2020.   (SIGIR 2020, CCF A, CORE A+)
  

• Changde Du, Changying Du, Lijie Huang and Huiguang He. Conditional Generative Neural Decoding with Structured CNN Feature Prediction. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, USA, February 7-12, 2020.   (AAAI 2020, CCF A, CORE A+)
  

• Changying Du, Jia He, Changde Du, Fuzhen Zhuang, Qing He and Guoping Long. Efficient and Adaptive Kernelization for Nonlinear Max-margin Multi-view Learning. arXiv:1910.05250, 2019.
  

• Jia He, Changying Du, Fuzhen Zhuang, Xin Yin, Qing He and Guoping Long. Online Bayesian Max-margin Subspace Learning for Multi-view Classification and Regression. Machine Learning, 2019.   (Mach. Learn., supported by my NSFC Young Scientists Fund for "Efficient Bayesian Max-margin Feature Transform Study")
  

• Changde Du, Changying Du and Huiguang He. Doubly Semi-supervised Multimodal Adversarial Learning for Classification, Generation and Retrieval. In Proceedings of the 20th IEEE International Conference on Multimedia and Expo, Shanghai, China, July 8-12, 2019.   (ICME 2019, Best Paper Award Runner-Up, Oral, CCF B)
  

• Changde Du, Changying Du, Lijie Huang and Huiguang He. Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning. IEEE Transactions on Neural Networks and Learning Systems, 2019.   (TNNLS, IF=8.793)

• Changde Du, Changying Du, Hao Wang, Jinpeng Li, Wei-Long Zheng, Bao-Liang Lu and Huiguang He. Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data. In Proceedings of the 26th ACM International Conference on Multimedia, Seoul, Korea, October 22-26, 2018.   (ACM MM 2018, Full paper, CCF A, CORE A+)
  

• Changying Du, Changde Du, Xingyu Xie, Chen Zhang and Hao Wang. Multiview Adversarially Learned Inference for Cross-domain Joint Distribution Matching. In Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, London, United Kingdom, August 19-23, 2018.   (KDD 2018, Long oral)
  

• Chen Zhang, Yijun Wang, Can Chen, Changying Du, Hongzhi Yin and Hao Wang. Reliability Modeling for Stock Comments: A Holistic Perspective. In Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, London, United Kingdom, August 19-23, 2018.   (KDD 2018, Long oral)
  

• Changying Du, Xingyu Xie, Changde Du and Hao Wang. Redundancy-resistant Generative Hashing for Image Retrieval. In Proceedings of the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence, Stockholm, Sweden, July 13-19, 2018.   (IJCAI 2018)
  

• Changde Du, Changying Du, Baoliang Lu, Huiguang He. Multi-modal Emotion Recognition with Multi-view Deep Generative Models. In the 24th Annual Meeting of the Organization for Human Brain Mapping, Singapore, June 17-21, 2018.   (OHBM 2018)
  

• Changde Du, Changying Du and Huiguang He. Sharing Deep Generative Representation for Perceived Image Reconstruction from Human Brain Activity. In the 23rd Annual Meeting of the Organization for Human Brain Mapping, Vancouver, Canada, June 25-29, 2017.   (OHBM 2017, oral presentation, acceptance rate = 3%; A top story of the MIT Technology Review reviewed our work on May 6, 2017; CAS News and Daily Mail reported our work)
  

• Jia He, Changying Du, Changde Du, Fuzhen Zhuang, Qing He and Guoping Long. Nonlinear Max-Margin Multi-View Learning with Adaptive Kernel. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, August 19-25, 2017.  (IJCAI 2017, supported by my NSFC Young Scientists Fund for "Efficient Bayesian Max-margin Feature Transform Study")
  

• Changde Du, Changying Du, Jinpeng Li, Wei-Long Zheng, Bao-Liang Lu and Huiguang He. Semi-supervised Bayesian Deep Multi-modal Emotion Recognition. In the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Skopje, Macedonia, September 18-22, 2017.   (ECML/PKDD 2017)
  

• Changde Du, Changying Du and Huiguang He. Sharing Deep Generative Representation for Perceived Image Reconstruction from Human Brain Activity. In Proceedings of the 2017 International Joint Conference on Neural Networks, Anchorage, Alaska, USA, May 14-19, 2017.   (IJCNN 2017)
  

• Hao Wang, Yanmei Fu, Qinyong Wang, Hongzhi Yin, Changying Du and Hui Xiong. A Location-Sentiment-Aware Recommender System for Both Home-Town and Out-of-Town Mobile Users. In Proceedings of the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Halifax, Nova Scotia, Canada, August 13-17, 2017.   (KDD 2017, CCF A, CORE A+)
  

• Changying Du, Changde Du, Guoping Long, Qing He and Yucheng Li. Online Bayesian Multiple Kernel Bipartite Ranking. In Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence, New York, USA, June 25-29, 2016.  (UAI 2016, CCF B, CORE A+; Tentative study for my NSFC Young Scientists Fund proposal)
  

• Jia He, Changying Du, Fuzhen Zhuang, Xin Yin, Qing He and Guoping Long. Online Bayesian Max-Margin Subspace Multi-View Learning. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, USA, July 9-15, 2016.  (IJCAI 2016, CCF A, CORE A+; Tentative study for my NSFC Young Scientists Fund proposal)
  

• Changying Du, Changde Du, Guoping Long, Xin Jin and Yucheng Li. Efficient Bayesian Maximum Margin Multiple Kernel Learning. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Riva del Garda, Italy, September 19-23, 2016.  (ECML/PKDD 2016, CCF B, CORE A; Tentative study for my NSFC Young Scientists Fund proposal)
  

• Changying Du, Fuzhen Zhuang, Jia He, Qing He and Guoping Long. Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Riva del Garda, Italy, September 19-23, 2016.  (ECML/PKDD 2016, funded by my Open Project in CAS Key Lab of Intelligent Information Processing)
  

• Changde Du, Changying Du, Shandian Zhe, Ali Luo, Qing He and Guoping Long. Bayesian Group Feature Selection for Support Vector Learning Machines. In Proceedings of the 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Auckland, New Zealand, April 19-22, 2016.  (PAKDD 2016, Long oral, CCF C, CORE A)
  

• Siqi Deng, Kan Gao, Changying Du, Wenjing Ma, Guoping Long and Yucheng Li. Online Variational Bayesian Support Vector Regression. In Proceedings of the 2016 International Joint Conference on Neural Networks, Vancouver, British Columbia, Canada, July 25-29, 2016.  (IJCNN 2016, CCF C, CORE A)

• Changying Du, Shandian Zhe, Fuzhen Zhuang, Yuan Qi, Qing He, Zhongzhi Shi. Bayesian Maximum Margin Principal Component Analysis. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, Texas, USA, January 25-30, 2015.  (AAAI 2015, Oral; CCF A, CORE A+)
  

• Xin Jin, Fuzhen Zhuang, Sinno Pan, Changying Du, Ping Luo and Qing He. Heterogeneous Multi-task Semantic Feature Learning for Classication. In Proceedings of the 24th ACM International Conference on Information and Knowledge Management, Melbourne, Australia, October 19-23, 2015.  (CIKM 2015, CCF B, CORE A)
  

• Ning Bu, Lei Yu, Wenjing Ma, Changying Du, Shuzi Niu and Guoping Long. Detect Similar Mobile Applications with Transfer Learning. In Proceedings of the 2015 International Conference on Big Data Intelligence and Computing, Chengdu, China, December 19-21, 2015.
  

• Changying Du, Algorithmic Studies on Bayesian Nonparametric and Maximum Margin Learning, Ph.D. Dissertation of the Institute of Computing Technology Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China, May, 2015.
  

• Xin Jin, Fuzhen Zhuang, Hui Xiong, Changying Du, Ping Luo and Qing He. Multi-task Multi-view Learning for Heterogeneous Tasks. In Proceedings of the 23rd ACM International Conference on Information and Knowledge Management, Shanghai, China, November 3-7, 2014.  (CIKM 2014, Oral; CCF B, CORE A)
  

• Changying Du, Jia He, Fuzhen Zhuang, Yuan Qi and Qing He. Nonparametric Bayesian Multi-Task Large-margin Classification. In Proceedings of the 21st European Conference on Artificial Intelligence, Prague, Czech Republic, August 18-22, 2014.  (ECAI 2014, Long paper; CCF B, CORE A)
  

• Fuzhen Zhuang, Ping Luo, Changying Du, Qing He, Zhongzhi Shi and Hui Xiong. Triplex Transfer Learning: Exploiting Both Shared and Distinct Concepts for Text Classification. IEEE Transactions on Cybernetics 44(7), pp. 1191-1203, 2014.  (TCYB, IF=11.079)
  

• Qing He, Xin Jin, Changying Du, Fuzhen Zhuang and Zhongzhi Shi. Clustering in Extreme Learning Machine Feature Space. Neurocomputing 128, pp. 88-95, 2014.  (NEUCOM, IF=4.438)
  

• Fuzhen Zhuang, Ping Luo, Changying Du, Qing He and Zhongzhi Shi. Triplex Transfer Learning. In Proceedings of the 6th ACM International Conference on Web Search and Data Mining, Rome, Italy, February 6-8, 2013.  (WSDM 2013, Spotlight; CCF B, CORE A+)
  

• Changying Du, Fuzhen Zhuang, Qing He and Zhongzhi Shi. Multi-task Semi-supervised Semantic Feature Learning for Classification. In Proceedings of the 12th IEEE International Conference on Data Mining, Brussels, Belgium, December 10-13, 2012.  (ICDM 2012, Long paper; CCF B, CORE A+)
  

• Qing He, Changying Du, Qun Wang, Fuzhen Zhuang and Zhongzhi Shi. A Parallel Incremental Extreme SVM Classifier. Neurocomputing 74, pp. 2532-2540, 2011.  (NEUCOM, IF=4.438; Prof. Qing He was my Ph.D advisor)
  

• Qing He, Qun Wang, Changying Du, Xudong Ma and Zhongzhi Shi. A Parallel Hyper-Surface Classifier for High Dimensional Data. In Proceedings of the 3rd International Symposium on Knowledge Acquisition and Modeling, Wuhan, China, October 20-21, 2010.

• Deep Learning with Python, Tsinghua University Press
  

• Smart Internet of Things Projects, Tsinghua University Press

• 03/2022 - 03/2025:   Team Leader Manager, Momenta, Beijing, China
  

• 07/2021 - 03/2022:   Data Mining Team Leader, HAOMO.AI, Beijing, China
  

• 04/2021 - 07/2021:   AI Scientist/Tech Lead, CHISON Medical Technologies, Beijing/Wuxi, China
  

• 01/2019 - 04/2021:   Principal Engineer, Noah’s Ark Lab, Huawei Technologies, Beijing, China
  

• 04/2018 - 01/2019:   Senior Researcher, 360 Search, Qihoo Technologies, Beijing, China
  
  
• 10/2017 - 04/2018:   Associate Professor, Institute of Software, CAS, Beijing, China
  
  
• 07/2015 - 10/2017:   Assistant Professor, Institute of Software, CAS, Beijing, China
  
  
• 09/2009 - 07/2015:   Ph.D. Candidate, Institute of Computing Technology, CAS, Beijing, China
  
  
• 09/2013 - 09/2014:   Joint Ph.D., Department of Computer Science, Purdue University, West Lafayette, IN, USA
  
  
• 09/2004 - 06/2008:   B.S. Candidate, Department of Mathematics, Central South University, Changsha, China

• Innovation pioneer of Huawei academia sinica, Huawei Technologies, 2019
  

• Best Paper Award Runner-Up of ICME 2019
  

• Instant Incentive Award for the "Scene-aware AI Poet" project, Qihoo 360 Search, 2018
  
  
• MIT Technology Review, Daily Mail and CAS News reported our neural decoding work, May 2017
  
  
• Outstanding Ph.D. Dissertation, Institute of Computing Technology, CAS, 2015
  
  
• Inspur Outstanding Ph.D. Scholarship, Institute of Computing Technology, CAS, 2015
  
  
• Excellent Student, University of CAS, in 2014, 2013 and 2011
  
  
• Award from China Scholarship Council for one year abroad study, 2013
  
  
• Student Travel Award of ICDM 2012
  
  
• President's Scholarship, Institute of Computing Technology, CAS, 2011

• Changde Du, my young brother, who received his Ph.D. from the Institute of Automation, CAS in 2019. He was elected as one of the Top 40 for the Baidu Scholarship in 2017, and won the National Ph.D. Scholarship of China and the President's Scholarship of CAS in 2018 and 2019 respectively.
  

• Jia He, my junior sister apprentice, who got Ph.D. from the Institute of Computing Technology, CAS in 2019.
  
  
• Siqi Deng, engineer at Alibaba AI labs, who got her master degree from Institute of Software, CAS in 2017.
  
  
• Xingyu Xie, a Ph.D. student of Peking University, who interned at our lab.
  
  
• Weiping Song, a Ph.D. student of Peking University, who is interning at our lab.
  
  
• Hengliang Wang, a Ph.D. student of Peking University, who interned at our lab.
  
  
• Xinyi Yu, a master student of the University of Wisconsin–Madison.

• Review Expert of   National Natural Science Foundation of China
  

• Reviewer of   IEEE TKDE,   IEEE TNNLS,   IEEE TCYB,   CVIU,   Neurocomputing,   Knowledge-Based Systems
  
  
• SPC/PC Member of   ICML 21-22,   AAAI 19-22,   ICLR 22,   NeurIPS 20-21,   IJCAI 18-20