Research Assistant Professor Southern University of Science and Technology (SUSTech) chenghehust [at] gmail.com Dr. Cheng He is currently a Research Assistant Professor with the Department of Computer Science and Engineering, Southern University of Science and Technology, China. He serves as a Publication Chair for the12th International Conference on Bio-inspired Computing: Theories and Applications (2017), and a Co-Chair for Competition on Online Data-Driven Multi-Objective Optimization (2019), and a Co-Chair for IEEE Symposium on Model-Based Evolutionary Algorithms (2019 and 2020). His main research interests are Artificial/Computational Intelligence (including evolutionary multi-objective optimization, model-based optimization, large-scale optimization, etc.). His main research interests are Artificial/Computational Intelligence (includes evolutionary multi-objective optimization, model-based optimization, large-scale optimization, etc.).
CV / 简历 / Google Scholar / Github / LinkedIn
- 09/2021: Thanks Professor Linqiang Pan's recommendation, I have been awarded the "2021 ACM SIGBio Rising Star" (2021ACM SIGBio新星奖)!
- 08/2021: Our paper titled " Flow Field Prediction of Supercritical Airfoils via Variational Autoencoder based Deep Learning Framework" is accepted to Physics of Fluids! Congratulations to Jing Wang for leading the paper!
- 07/2021: Our paper titled " FaPN: Feature-aligned Pyramid Network for Dense Image Prediction" is accepted to IEEE ICCV'21! Congratulations to Shihua Huang and Zhichao Lu for their hardworking on the paper!
- 07/2021: Our paper titled " RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning" is accepted to IEEE TNNLS! Congratulations to Hao Tan for his hardworking on the paper!
- 06/2021: Our paper titled "Evolutionary Large-Scale Multi-Objective Optimization: A Survey " is accepted to ACM Computing Surveys! Congratulations to Ye Tian for leading the paper!
- 04/2021: Thanks Shenzhen Science and Technology Program for the general program grant (PI) to fund our large-scale multi-objective optimization project (深圳市优秀科技创新人才培养项目（博士启动项目）, No. RCBS20200714114817264)!
|
Cheng He , Lianghao Li, Ye Tian, Xingyi Zhang, Ran Cheng, Yaochu Jin, Xing Yao IEEE Transactions on Evolutionary Computation, 2019 paper code poster LSMOF is an effective framework for large-scale multiobjective optimization. Generally, this framework can reduce the number of decision variables from 1000 to less than 20. The cost of FEs is less than 100,000 for conventional LSMOPs. |
|
Cheng He , Shuhua Huang, Ran Cheng, Tan Kay Chen Yaochu Jin, IEEE Transactions on Cybernetics, 2021 paper code poster GMOEA focuses on efficient offspring generation via learning from the distribution of promising solutions. GMOEA is capable of handling MOPs with up to 200 decision variables effectively, which is a new research direction for model-based evolutionary computation. |
|
Cheng He , Ran Cheng, Chuanji Zhang, Ye Tian, Qin Chen Xin Yao, IEEE Transactions on Evolutionary Computation, 2020 paper code TREE is a large-scale multiobjective optimization test suite extracted from the power dilivery system, aiming at handling real-time ratio error estimation of voltage transformers. Generally, the maximum number of decision variables is up to half a million and it includes constraints, which provides a guidance for the desgin of meaningful evolutionary algorithm. |
|
Shihua Huang, Zhichao Lu, Ran Cheng, Cheng He ICCV, 2021 arXiv code FaPN a simple yet effective top-down pyramidal architecture to generate multi-scale features for dense image prediction. It improves FPN's AP / mIoU by 1.5 - 2.6% on all tasks. |