Associate Professor, Associate Dean
Huazhong University of Science and Technology (HUST)
IEEE Senior Member, chenghehust [at] gmail.com
Dr. Cheng He is currently an Associate Professor with the School of Electrical and Electronic Engineering, Huazhong University of Science and Technology, China.
His main research interests are Artificial/Computational Intelligence (including evolutionary multi-objective optimization, model-based optimization, large-scale optimization, etc.).

Representative Articles

We have categorized our articles relating to surrogate-assisted optimization, large-scale optimization, multi-/many-objective optimization, and deep learning and its applications. You are welcome to cite these papers via the Bibtex.

Recent News
  • 01/2024: Thanks for the invitation from Evolutionary Computation Journal as a member of the Editorial Board.
  • 09/2023: Recently, we have hosted a Special Issue "New Insights in Computational Intelligence and Its Applications" on Electronics. We encourage submissions that explore novel algorithms, theoretical frameworks, hybrid methodologies, and successful applications of CI in both traditional and emerging fields. We look forward to reading your contributions to this Special Issue, poised to deepen the understanding and application of computational intelligence in overcoming real-world complexities.
Selected Research
Accelerating Large-scale Multiobjective Optimization via Problem Reformulation
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.

Evolutionary Multiobjective Optimization Driven by Generative Adversarial Networks (GANs)
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.

Evolutionary Large-Scale Multiobjective Optimization for Ratio Error Estimation of Voltage Transformers
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.

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
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.