Experience
Education
Grand
Research Funding of Post-doctor Residing in Shenzhen, 2021 - 2023.
Fellowship of China Postdoctoral Science Foundation, 2020.
Award
Shenzhen High-level Personnel - Reserve Talents (深圳市高层次人才-后备级), 2021-2026.
Project
深圳证券信息有限公司-南方科技大学计算机系行情云联合创新实验室, 深交所集团, 2022-2024, 技术负责人.
基于云技术的行情SDK服务标准研究, 证监会标准委员会, 2022-2023, 南科大-技术负责人.
Noise Tolerant Deep Neural Network Compression for Reliable Edge Computing (工况环境的深度神经网络模型可靠性评估研究), Huawei Inc., 2022 - 2023, PI.
基于云原生的高性能信息服务系统的关键技术研究, 深交所集团, 2020-2021, 技术负责人.
DNN Compression for Dialog Models, OPPO Inc., 2020, 技术负责人.
Research Interest
Cloud Native & Edge Computing
Deep Neural Network Compression
Neural Machine Translation
Object Detection
Journal
- Guiying Li, Peng Yang, Chao Qian, Richang Hong, and Ke Tang: Stage-Wise Magnitude-Based Pruning for Recurrent Neural Networks. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. [Early access][Github]
- Wenjing Hong, Guiying Li, Shengcai Liu, Peng Yang, and Ke Tang: Multi-Objective Evolutionary Optimization for Hardware-Aware Neural Network Pruning. Fundamental Research, 2022. [In Press]
- Yunwen Lei, Ting Hu, Guiying Li*, and Ke Tang: Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 31(10): 4394-4400, October 2020. [paper]
- Juncheng Wang, Guiying Li*: Accelerate proposal generation in R-CNN methods for fast pedestrian extraction. The Electronic Library, 37(3): 435-453, June 2019. [paper]
Conference
- Shun Lu, Cheng Chen, Kunlong Zhang, Yang Zheng, Zheng Hu, Wenjing Hong, Guiying Li*, Xin Yao : Noise-tolerant Hardware-aware Pruning for Deep Neural Networks. In: Proceedings of the 14th International Conference on Swarm Intelligence (ICSI 2023), 2023, accepted.
- Peng Yang, Lang Fu, Jian Zhang, and Guiying Li*: OCET: One-dimensional Convolution Embedding Transformer for Stock Trend Prediction. In: Proceedings of the 17th International Conference on Bio-inspired Computing: Theories and Applications (BIC-TA 2022), pages 370-384, Wuhan, China, 2022. [paper][GitHub]
- Jianqi Cao, Guiying Li*, and Peng Yang: Reinforcement Learning Based Vertical Scaling for Hybrid Deployment in Cloud Computing. In: Proceedings of the 17th International Conference on Bio-inspired Computing: Theories and Applications (BIC-TA 2022), pages 408–418, Wuhan, China, 2022. [paper]
- Lan Tang, Xiaxi Li, Jinyuan Zhang, Guiying Li, and Peng Yang*. Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding. In: Proceedings of the 17th International Conference on Bio-inspired Computing: Theories and Applications (BIC-TA 2022), pages 233–247, Wuhan, China, 2022. [paper]
- Han Li, Guiying Li*: Learning to Solve Capacitated Arc Routing Problems by Policy Gradient. In Proceedings of IEEE Congress on Evolutionary Computation 2019 (CEC 2019), pages 1291-1298, Wellington, New Zealand, June 2019. [paper]
- Guiying Li, Chao Qian, Chunhui Jiang, Xiaofen Lu, and Ke Tang. Optimization based Layer-wise Magnitude-based Pruning for DNN Compression. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), pages 2383-2389, Stockholm, Sweden, 2018. [pdf link][Github]
- Guiying Li, Junlong Liu, Chunhui Jiang, Liangpeng Zhang, and Ke Tang. Relief R-CNN: Utilizing Convolutional Features for Fast Object Detection. In Proceedings of the 14th International Symposium on Neural Networks (ISNN 2017), pages 386-394, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, 2017. [paper][Github]
- Chao Qian, Guiying Li, Chao Feng, and Ke Tang. Distributed Pareto Optimization for Subset Selection. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), pages 1492-1498, Stockholm, Sweden, 2018. [pdf link][code package]
- Chunhui Jiang, Guiying Li, Chao Qian, and Ke Tang. Efficient DNN Neuron Pruning by Minimizing Layer-wise Nonlinear Reconstruction Error. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), pages 2298-2304, Stockholm, Sweden, 2018. [pdf link][code package]
- Chunhui Jiang, Guiying Li, and Chao Qian. Dynamic and Adaptive Threshold for DNN Compression from Scratch. In Proceedings of the 11th International Conference on Simulated Evolution and Learning (SEAL 2017), pages 858-869, Shenzhen, China, 2017. [paper]
- Chunhui Jiang, Guiying Li, Junlong Liu, Yunfeng Liu, and Ke Tang. A Trajectory-based Approach for Object Detection from Video. In Proceedings of 2016 International Joint Conference on Neural Networks (IJCNN 2016), pages 2887-2893, Vancouver, BC, Canada, 2016. [paper]
Invention
Authorized
- 杨鹏; 张剑; 张烙铭; 李皈颖. 容器集群负载均衡方法、装置、设备及存储介质. 发明专利. 2022-12-13. 中国. 专利号: ZL2021 1 1245218.X.
- LI Guiying, YANG Peng, TANG Ke, YAO Xin. 基于二维码的物流管理系(Logistikmanagementsystem auf der Basis eines zweidimensionalen Codes). 实用新型. 2022-10-27. 德国. 优先权号: 2021-04-30 CN202110480598.9.
- 李皈颖;汪至圆;唐珂;杨鹏. 语音控制指令的生成方法、装置、计算机设备及存储介质. 发明专利. 2022-10-25. 中国. 专利号: ZL2021 1 0591864.5.
- 李皈颖, 杨鹏, 唐珂,姚新. 用于显示屏幕面板的人工智能研发云系统操作图形用户界面. 外观新型. 2022-05-13. 中国. 专利号: ZL2021 3 0818006.0.
- 李皈颖, 杨鹏, 唐珂,姚新. 用于显示屏幕面板的人工智能应用云系统操作图形用户界面. 外观新型. 2022-05-13. 中国. 专利号: ZL 2021 3 0818192.8.
- 李皈颖, 杨鹏, 唐珂,姚新. 天引应用算法用户系统软件. 软件著作. 2022-01-27. 中国. 登记号: 2022SR0174905.
- 李皈颖, 杨鹏, 唐珂,姚新. 天引应用算法开发系统软件. 软件著作. 2022-01-27. 中国. 登记号: 2022SR0174761.
- 杨鹏;李皈颖;唐珂. 路径规划方法、装置、设备和存储介质. 发明专利. 2021-06-15. 中国. 专利号: ZL2019 1 0482413.0.
Appplication
- 李皈颖;曹建琦;杨鹏;唐珂;姚新. 基于云原生技术的AI算法与微服务调度方法及其装置. 发明专利. 2022-12-09. 中国. 申请公布号: CN115454629A.
- 杨鹏;唐岚;李皈颖;唐珂;姚新. 基于适应度预测的强化学习模型训练方法及其系统. 2022-12-02. 中国. 申请公布号: CN115423023A.
- 杨鹏;李皈颖;韩朝勇;李奇隆;叶梦;张皓;吴霞飞;许丹昊;赵国强. 会话连接控制方法、会话连接控制装置及计算机存储介质. 2022-09-27. 中国. 申请公布号: CN115118760A.
- 李皈颖;杨鹏;韩朝勇;罗健;叶梦;吴霞飞;许丹昊;赵国强. 多云多活数据同步方法以及相关设备. 2022-06-03. 中国. 申请公布号: CN114579665A.
- 洪文静;李皈颖;杨鹏;唐珂. 神经网络的压缩方法和装置、设备、介质. 2022-03-08. 中国. 申请公布号: CN114154634A.
- 杨鹏;张剑;张烙铭;李皈颖. 容器集群弹性伸缩方法、装置、设备及存储介质. 2022-02-01. 中国. 申请公布号: CN114003340A.
- 李皈颖;杨鹏;唐珂;姚新. 基于二维码的物流管理方法、系统、服务器和存储介质. 2021-07-30. 中国. 申请公布号: CN113191469A.