Biography

Donglin Wang received the B.E. and M.S. degrees in the school of electronics and information engineering from Xi'an Jiaotong University, China, in 2003 and 2006, respectively, and the Ph.D. degree in the department of electrical and computer engineering from the University of Calgary, Canada, in 2010. After that, he acted as a postdoc research fellow in the iRadio lab, Canada. From late 2011 to Aug. 2017, he was an assistant/associate professor in the department of electrical and computer engineering at New York Institute of Technology. He is now an associate professor and director of Machine Intelligent Lab (MiLAB) in School of Engineering at Westlake University.

Research

Our lab is focusing on robot learning, including machine learning algorithms, intelligent robot and data mining.

1. Machine learning algorithms: reinforcement learning, Meta-learning, one-shot learning, and curriculum learning;

2. Robot Intelligence: learning based flexibility, fast adaptation, behavior development, lifelong memory and human-like navigation;

3. Data mining: Time-series prediction, recommendation and applications.

Representative Publications

[1] J. Liu, H. Zhang, D. Wang*, "DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning," International Conference on Learning Representations (ICLR), 2022.

[2] J. Liu, D. Wang*, Q. Tian, Z. Chen, "Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning," Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.

[3] T. Wang, Z. Wu*, D. Wang*, "Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning," IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021.

[4] T. Xiao, Z. Chen, D. Wang*, S. Wang, "Learning How to Propagate Messages in Graph Neural Networks", ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2021

[5] J. Liu, H. Shen, D. Wang*, Y. Kang, Q. Tian, "Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning," Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), 2021.

[6] Z. Chen, J. Ge, H. Zhan, S. Huang, D. Wang*, "Pareto Self-Supervised Training for Few-Shot Learning," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[7] S. Huang, M. Zhang, Y. Kang, and D. Wang*, “Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition,” In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021.

[8] T. Xiao and D. Wang*, “A General Offline Learning Framework for Interactive Recommendation,” In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021.

[9] Q. Tian, G. Wang, J. Liu, D. Wang* and Y. Kang, “Independent Skill Transfer for Deep Reinforcement Learning,” In Proceedings of the International Joint Conferences on Artificial Intelligence (IJCAI), IJCAI-PRICAI 2020, Yokohama Japan, 2020.

[10] S. Huang, D. Wang*, X. Wu and A. Tang, “DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting,” In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM), Beijing, 2019.