Yin Haiyan

scientist---yin-haiyan

Research Area
  • Reinforcement Learning
  • Meta Learning
  • Natural Language Generation

Award

  • ICLR 2022 Highlighted Reviewer

Publications

1. Distributional Meta Gradient Reinforcement Learning. Haiyan Yin, Shuicheng Yan, Zhongwen Xu, 11th International Conference on Learning Representations (ICLR) 2023.

2. Crowd-level Abnormal Behavior Detection via Multi-scale Motion Consistency Learning. Linbo Luo, Yuanjing Li, Haiyan Yin, Shangwei Xie, Ruimin Hu, Wentong Cai, 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

3. CASA: A Bridge Between Gradient of Policy Improvement and Policy Evaluation. Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin. Neurips 2022 Deep Reinforcement Learning (DRL) Workshop.

4. Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning. Haiyan Yin, Dinigcheng Li, Ping Li,  2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).

5. Causal Discovery with Flow-based Conditional Density Estimation. Shaogang Ren, Haiyan Yin, Mingming Sun, Ping Li. 2021 IEEE International Conference on Data Mining (ICDM).

6. Mitigating Forgetting in Online Continual Learning with Meta Neural Calibration. Haiyan. Yin, Peng Yang, Ping Li. Thirty-fifth Conference on Neural Information Processing Systems (Neurips), 2021.

7. Sequential Generative Exploration Model for Partially Observable Reinforcement Learning. Haiyan Yin, Jianda Chen, Sinno Jialin Pan, Sebastian Tschiatschek. 35th AAAI Conference on Artificial Intelligence (AAAI), 2021.

8. Reinforcement Learning with Efficient Active Feature Acquisition. Haiyan Yin, Yingzhen Li, Sinno Jialin Pan, Cheng Zhang, Sebastian Tschiatschek. Neurips 2020 Workshop on Learning Meets Combinatorial Algorithms (LMCA).

9. Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation Models. Haiyan Yin, Dingcheng Li, Xu Li, Ping Li. 34th AAAI Conference on Artificial Intelligence (AAAI), 2020.

10. Deep Learning Assisted Resource Partitioning for Improving Performance on Commodity Servers. Ruobing Chen, Jinping Wu, Haosen Shi, Yusen Li, Haiyan Yin, Shanjiang Tang, Xiaoguang Liu, Guang Wang. International Conference on Parallel Architectures and Compilation Techniques (PACT), 2020.

11. Learning Domain Invariant Features for Zero-shot Policy Transfer in Deep Reinforcement Learning. Haiyan Yin, Jianda Chen, Sinno Jialin Pan. NIPS 2018 Deep Reinforcement Learning (DRL) Workshop.

12. Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning. Haiyan Yin, Jianda Chen, Sinno Jialin Pan. International Joint Conference on Artificial Intelligence joint with the the 23rd European Conference on Artificial Intelligence (IJCAI), 2018.

13. Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay. Haiyan Yin, Sinno Jialin Pan. 31st AAAI Conference on Artificial Intelligence (AAAI), 2017.

14. Design and Evaluation of a Data-driven Scenario Generation Framework for Game-based Training. Linbo Luo, Haiyan Yin, Wanting Cai, Jinghui Zhong. IEEE Transactions on Computational Intelligence and AI in Games (T-CIAIG), 2017.

15. A Data-driven Approach for Online Adaptation of Game Difficulty. Haiyan Yin, Linbo Luo, Wanting Cai, Yew-Soon Ong, Jinghui Zhong. IEEE Conference on Computational Intelligence and Games (CIG), 2015.

16. Learning Behavior Patterns from Video: A Data-driven Framework for Agent-based Crowd Modeling. Jinghui Zhong, Wentong Cai, Linbo Luo, Haiyan Yin. Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015.

17. A Review of Interactive Narrative Systems and Technologies: A Training Perspective. Linbo Luo, Wanting Cai, Suiping Zhou, Michael Lees, Haiyan Yin. Simulation: Transactions of the Society for Modeling and Simulation International, 2015.

18. Mission-based Scenario Modeling and Generation for Virtual Training. Linbo Luo, Haiyan Yin, Jinghui Zhong, Wanting Cai, Michael Lees, Suiping Zhou. Proceedings of the 9th AAAI Conference on Artificial Intelligence for Interactive Digital Entertainment (AIIDE), Boston, Massachusetts, 2013

Research Services

  • Conference Reviewer: 
    ICML, Neurips, ICLR, AAAI, IJCAI, ACML, ACL, EMNLP, EACL, ICTAI, ICAPS, SDM, KDD. 
  • Journal Reviewer:
    Journals & IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),
    Transactions on Machine Learning Research (TMLR),
    IEEE Trans. on Multimedia (TMM),
    IEEE Trans. on Neural Networks and Learning Systems (TNNLS),
    IEEE Trans. on Emerging Topics in Computational Intelligence (TETCI),
    Neurocomputing