GuiyingLi

Home People Research Research Publications Teaching Protocol Sharing News Center for Pain Medicine Research Brief Info Software Alumni Join us Contact us Guiying Li Research Assistant Professor Department of Computer Science and Engineering   Research Group My primary research interests are in the fields of deep neural network simplification and algorithm acceleration, which relate to the real applications of artificial intelligence. My research focuses on the optimization of artificial intelligent methods like deep neural networks, heuristic search processes with respect to the characteristic of target devices. The efficient issue is also crucial for artificial intelligence methods in real applications. My research heavily focuses on the algorithm design for practical requirements, which always emphasizes developing workable, reproducible, and robust algorithms that meet the requirements that come from industrial scenarios. Personal Profile Personal Profile Research Deep Neural Network Compression Edge computing Cloud Native Publications Read More Yunwen Lei, Ting Hu, Guiying Li*, 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] 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] 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] 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] Join us Read More Contact Us Contact Address Office 646b, South Tower, CoE Building,SUSTech,1088 Xueyuan Avenue, Nanshan District, Shenzhen 518055, P.R. China Office Phone Email ligy@sustech.edu.cn