Wang Yu(王煜)

alt text 

Ph.D., Associate Professor,
Tianjin Key Laboratory of Machine Learning,
School of Artificial Intelligence,
College of Intelligence and Computing,
Tianjin University (TJU)
No. 135 Yaguan Road, Jinnan District,
Tianjin City, P.R. China.
E-mail: wang.yu AT tju.edu.cn

News!

[2024/05]  "Socialized learning: making each other better through multi-agent collaboration" has been accepted by International Conference on Machine Learning (ICML).
[2024/04]  "Integrated heterogeneous graph attention network for incomplete multi-modal clustering" has been published on International Journal of Computer Vision (IJCV).
[2024/02]  "Multi-view deep subspace clustering networks" has been published on IEEE Transactions on Cybernetics (TCYB).
[2024/01]  "Exploring diverse representations for open set recognition" has been published on Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
[2024/01]  "Every node is different: dynamically fusing self-supervised tasks for attributed graph clustering" has been published on Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
[2024/01]  "Dynamic sub-graph distillation for robust semi-supervised continual learning" has been published on Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
[2023/12]  "Few-shot learning with multi-granularity knowledge fusion and decision-making" has been published on IEEE Transactions on Big Data (TBD).
[2023/12]  "Industrial big data analytical system in industrial cyber-physical systems based on coarse-to-fine deep network" has been published on IEEE Transactions on Industrial Cyber-Physical Systems (TICPS).
[2023/07]  "Coarse-to-fine: progressive knowledge transfer based multi-task convolutional neural network for intelligent large-scale fault diagnosis" has been published by IEEE Transactions on Neural Networks and Learning Systems (TNNLS).
[2023/06]  Our team has won the championship of CVPR 2023 Open World Object Discovery Challenge.
[2023/06]  Our team has won the runner up of CVPR 2023 Continual Learning Challenge.
[2023/04]  "Class-specific semantic reconstruction for open set recognition" has been published on IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
[2023/04]  "Multi-granularity regularized re-balancing for class incremental learning" has been published on IEEE Transactions on Knowledge and Data Engineering (TKDE).

Bio

Wang Yu (王煜) is currently an associate professor at Tianjin University (TJU) and Tianjin Key Laboratory of Machine Learning led by Prof. Hu Qinghua (胡清华). He received BA, ME, and Ph.D degrees from Tianjin University. His researches lie in data mining and machine learning in artificial intelligence, including multi-granularity classification, open-set recognition, incremental learning, and their applications to image classification and fault diagnosis of complex systems. He has published many papers in highly regarded journals and conferences, such as IEEE TPAMI, IEEE TKDE, IEEE TNNLS, IEEE TCYB, etc.

Call for graduate and undergraduate students! Hope you are hardworking, determined, and have basic programming skills and mathematics knowledge. You can receive detailed supervision on research and would have a promising career. Feel free to contact me via email.

Selected Publications

alt text 

[TPAMI CCF A]  
Class-specific semantic reconstruction for open set recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
Hongzhi Huang, Yu Wang* Qinghua Hu*, and Ming-Ming Cheng.
[Paper] [Code]

alt text 

[IJCV CCF A]  
Integrated heterogeneous graph attention network for incomplete multi-modal clustering
International Journal of Computer Vision (2024).
Yu Wang, Xinjie Yao, Pengfei Zhu*, Weihao Li, Meng Cao, and Qinghua Hu.
[Paper] [Code]

alt text 

[AAAI CCF A]  
Exploring diverse representations for open set recognition
Proceedings of the AAAI Conference on Artificial Intelligence (2024).
Yu Wang, Junxian Mu, Pengfei Zhu, and Qinghua Hu.
[Paper] [Code]

alt text 

[AAAI CCF A]  
Dynamic sub-graph distillation for robust semi-supervised continual learning
Proceedings of the AAAI Conference on Artificial Intelligence (2024).
Yan Fan, Yu Wang*, Pengfei Zhu, and Qinghua Hu.
[Paper] [Code]

alt text 

[TKDE CCF A]  
Multi-granularity regularized re-balancing for class incremental learning
IEEE Transactions on Knowledge and Data Engineering (2023).
Huitong Chen, Yu Wang*, and Qinghua Hu.
[Paper] [Code]

alt text 

[TCYB CAS-JCR Q1 Top]  
Hierarchical semantic risk minimization for large-scale classification
IEEE Transactions on Cybernetics (2023).
Yu Wang, Zhou Wang, Qinghua Hu, Yucan Zhou, and Honglei Su.
[Paper]

alt text 

[TNNLS CAS-JCR (中科院分区) Q1 Top]  
Collaborative decision-reinforced self-supervision for attributed graph clustering
IEEE Transactions on Neural Networks and Learning Systems (2022).
Pengfei Zhu, Jialu Li, Yu Wang*, Bin Xiao, Shuai Zhao, and Qinghua Hu.
[Paper] [Code]

alt text 

[AAAI CCF A]  
Every node is different: dynamically fusing self-supervised tasks for attributed graph clustering
Proceedings of the AAAI Conference on Artificial Intelligence (2024).
Pengfei Zhu, Qian Wang, Yu Wang*, Jialu Li, and Qinghua Hu.
[Paper] [Code]

alt text 

[TNNLS CAS-JCR Q1 Top]  
Coarse-to-fine: progressive knowledge transfer based multi-task convolutional neural network for intelligent large-scale fault diagnosis
IEEE Transactions on Neural Networks and Learning Systems (2023).
Yu Wang, Ruonan Liu, Di Lin, Dongyue Chen, Ping Li, Qinghua Hu, and C. L. Philip Chen.
[Paper] [Code]

alt text 

[软件学报 CCF A]  
考虑多粒度类相关性的对比式开放集识别方法
软件学报 (2022).
朱鹏飞, 张琬迎, 王煜*, 胡清华.
[Paper]

alt text 

[TMM CAS-JCR Q1 Top]  
Latent heterogeneous graph network for incomplete multi-view learning
IEEE Transactions on Multimedia (2022).
Pengfei Zhu, Xinjie Yao, Yu Wang*, Meng Cao, Binyuan Hui, Shuai Zhao, and Qinghua Hu.
[Paper] [Code]

alt text 

[TFS CAS-JCR Q1 Top]  
Deep fuzzy tree for large-scale hierarchical visual classification
IEEE Transactions on Fuzzy Systems (2020).
Yu Wang, Qinghua Hu, Pengfei Zhu, Linhao Li, Bingxu Lu, Jonathan G. Garibaldi, and Xianlin Li.
[Paper]

Service

He serves as a reviewer of: