特聘研究员

尚可，博士，深圳大学特聘研究员、助理教授、博导。

邮箱: shangk@szu.edu.cn or kshang@foxmail.com

博士毕业于西安交通大学。

主持国家自然科学基金青年基金项目1项、面上项目1项，广东省自然科学基金面上项目1项，以第一/通讯作者在IEEE TEVC、IEEE TCYB、IEEE CIM、IJCAI、PPSN、GECCO等重要期刊和国际会议发表论文70余篇，谷歌学术引用1500余次，荣获ACM GECCO2018/2021/2024最佳论文奖、IEEE CEC2019最佳论文奖亚军、PPSN2020最佳论文提名，现为IEEE高级会员。

2025年拟招收3名硕士研究生（含学硕（计算机科学与技术）和专硕（计算机技术）），欢迎对人工智能、大模型、智能优化算法感兴趣的同学与我联系。

科研能力及成果

研究兴趣：多目标优化、计算智能、强化学习、基于大模型的优化等。

期刊论文

0. K. Shang, G. Wu, L. M. Pang, and H. Ishibuchi “Targeted Pareto Optimization for Subset Selection with Monotone Objective Function and Cardinality Constraint.” IEEE Transactions on Evolutionary Computation (2024).

1. K. Shang, T. Shu, H. Ishibuchi, Y. Nan, and L. M. Pang “Benchmarking Large-Scale Subset Selection in Evolutionary Multi-Objective Optimization.” Information Sciences (2022).

2. K. Shang, T. Shu, and H. Ishibuchi “Learning to Approximate: Auto Direction Vector Set Generation for Hypervolume Contribution Approximation.” IEEE Transactions on Evolutionary Computation (2022).

3. K. Shang#, W. Chen#, W. Liao, and H. Ishibuchi “HV-Net: Hypervolume Approximation based on DeepSets.” IEEE Transactions on Evolutionary Computation (2022). (#Equal Contribution)

4. K. Shang, H. Ishibuchi, W. Chen, Y. Nan, and W. Liao “Hypervolume-Optimal μ-Distributions on Line/Plane-based Pareto Fronts in Three Dimensions”. IEEE Transactions on Evolutionary Computation (2021).

5. K. Shang, H. Ishibuchi, L. He, and L. M. Pang “A Survey on the Hypervolume Indicator in Evolutionary Multi-objective Optimization.” IEEE Transactions on Evolutionary Computation (2020). ESI Highly Cited Paper

6. K. Shang, and H. Ishibuchi ""A New Hypervolume-based Evolutionary Algorithm for Many-objective Optimization."" IEEE Transactions on Evolutionary Computation (2020).

7. K. Shang, H. Ishibuchi, and X. Ni ""R2-based Hypervolume Contribution Approximation."" IEEE Transactions on Evolutionary Computation (2020).

8. K. Shang, Z. Feng, L. Ke, and F. T. Chan ""Comprehensive Pareto Efficiency in robust counterpart optimization."" Computers & Chemical Engineering (2016).

9. T. Shu, K. Shang*, H. Ishibuchi*, and Y. Nan “Effects of Archive Size on Computation Time and Solution Quality for Multi-Objective Optimization.” IEEE Transactions on Evolutionary Computation (2022). (*Corresponding author)

10. Y. Nan, K. Shang, H. Ishibuchi, and L. He “An Improved Local Search Method for Large-Scale Hypervolume Subset Selection.” IEEE Transactions on Evolutionary Computation (2022).

11. L. He, K. Shang, Y. Nan, H. Ishibuchi, and D. Srinivasan “Relation Between Objective Space Normalization and Weight Vector Scaling in Decomposition-Based Multi-Objective Evolutionary Algorithms.” IEEE Transactions on Evolutionary Computation (2022).

12. L. He, K. Shang, and H. Ishibuchi ""Simultaneous Use of Two Normalization Methods in Decomposition-based Multi-objective Evolutionary Algorithms."" Applied Soft Computing (2020).

13. Y. Nan, K. Shang, H. Ishibuchi “Reverse Strategy for Non-dominated Archiving.” IEEE Access (2020).

14. L. M. Pang, H. Ishibuchi, and K. Shang ""Use of Two Penalty Values in Multi-objective Evolutionary Algorithm based on Decomposition."" IEEE Transactions on Cybernetics (2022).

15. L. M. Pang, H. Ishibuchi, and K. Shang ""Counterintuitive Experimental Results in Evolutionary Large-Scale Multi-Objective Optimization."" IEEE Transactions on Evolutionary Computation (2022).

16. H. Ishibuchi, L. M. Pang, and K. Shang ""Difficulties in Fair Performance Comparison of Multi-Objective Evolutionary Algorithms."" IEEE Computational Intelligence Magazine (2021).

17. W. Chen, H. Ishibuchi, and K. Shang “Fast Greedy Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization”. IEEE Transactions on Evolutionary Computation (2021).

会议论文

0. T. Shu, K. Shang*, C. Gong, Y. Nan, and H. Ishibuchi, “Learning Pareto Set for Multi-Objective Continuous Robot Control.” IJCAI 2024.

1. K. Shang, W. Liao, and H. Ishibuchi “HVC-Net: Deep Learning based Hypervolume Contribution Approximation.” Parallel Problem Solving from Nature (PPSN2022).

2. K. Shang, H. Ishibuchi, L. M. Pang, and Y. Nan “Reference Point Specification for Greedy Hypervolume Subset Selection.” IEEE International Conference on Systems, Man, and Cybernetics (SMC2021).

3. K. Shang, H. Ishibuchi, and W. Chen “Greedy Approximated Hypervolume Subset Selection for Many-objective Optimization”. Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2021). Best Paper Award

4. K. Shang, H. Ishibuchi, and Y. Nan “Distance-based Subset Selection Revisited”. Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2021).

5. K. Shang, H. Ishibuchi, L. Chen, W. Chen, and L. M. Pang “Improving the Efficiency of R2HCA-EMOA”. 11th International Conference on Evolutionary Multi-Criterion Optimization (EMO2021).

6. K. Shang, H. Ishibuchi, Y. Nan, and W. Chen “Transformation-based Hypervolume Indicator: A Framework for Designing Hypervolume Variants”. IEEE Symposium Series on Computational Intelligence (SSCI2020).

7. K. Shang, H. Ishibuchi, W. Chen, and L. Adam ""Hypervolume optimal mu-distributions on line-based Pareto fronts in three dimensions."" Parallel Problem Solving from Nature. (PPSN2020).

8. K. Shang, H. Ishibuchi, M. L. Zhang, and Y. Liu ""A new R2 indicator for better hypervolume approximation."" Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2018). Best Paper Award

9. H. Zhu, K. Shang*, H. Ishibuchi* “STHV-Net: Hypervolume Approximation based on Set Transformer.” Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2023). (*Corresponding author)

10. T. Shu, K. Shang*, Y. Nan, and H. Ishibuchi* “Direction Vector Selection for R2-based Hypervolume Contribution Approximation.” Parallel Problem Solving from Nature (PPSN2022). (*Corresponding author)

11. L. M. Pang#, K. Shang #, L. Chen, H. Ishibuchi, and W. Chen “Proposal of a New Test Problem for Large-Scale Many-Objective Optimization”. IEEE International Conference on Systems, Man, and Cybernetics (SMC2021). (#Equal Contribution)

12. Y. Nan, K. Shang, H. Ishibuchi, and L. He “Improving Hypervolume-based Greedy Sequential Insertion Subset Selection in Evolutionary Multi-objective Optimization”. IEEE International Conference on Systems, Man, and Cybernetics (SMC2021).

13. Y. Nan, K. Shang, H. Ishibuchi, and L. He “A Two Stage Hypervolume Contribution Approximation Method Based on R2 Indicator”. IEEE Congress on Evolutionary Computation (CEC2021).

14. Y. Nan#, K. Shang #, and H. Ishibuchi ""What is a Good Direction Vector Set for the R2-based Hypervolume Contribution Approximation."" Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2020). (#Equal Contribution)

15. W. Chen, H. Ishibuchi, and K. Shang “Proposal of a realistic many-objective test suite.” Parallel Problem Sovling from Nature. (PPSN2020). Best Paper Nomination

16. H. Ishibuchi, Y. Peng, and K. Shang ""A Scalable Multimodal Multiobjective Test Problem."" IEEE Congress on Evolutionary Computation (CEC2019). First Runner-up Conference Paper Award

17. T. Shu, Y. Nan, K. Shang*, H. Ishibuchi* “Two-Phase Procedure for Efficiently Removing Dominated Solutions from Large Solution Sets.” Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2023). (*Corresponding author)

18. G. An, Z. Wu, Z. Shen, K. Shang*, H. Ishibuchi* “Evolutionary Multi-Objective Deep Reinforcement Learning for Autonomous UAV Navigation in Large-Scale Complex Environments.” Proceedings of the Genetic and Evolutionary Computation Conference. (GECCO2023). (*Corresponding author)

邀请报告

1. 演化多目标优化的发展现状及最新研究进展, 中国计算机学会青年计算机科技论坛兰州分论坛, 2020年7月4日.

2. Hypervolume Approximation for Many-objective Optimization, IEEE CIS Seminar, 2022-8-24.

3. 面向高维多目标优化的超体积指标近似, 大数据专委会学术活动-NICE Seminar, 2023-2-19.

Tutorials

1. Difficulties in Fair Performance Comparison of Multiobjective Evolutionary Algorithms, GECCO 2022 Tutorial.

2. How to Compare Evolutionary Multi-Objective Optimization Algorithms: Parameter Specifications, Indicators and Test Problems. WCCI 2022 Tutorial.

3. How to Compare Evolutionary Multi-Objective Optimization Algorithms: Parameter Specifications, Indicators and Test Problems. IEEE CEC 2023 Tutorial.

4. Quality indicators for multi-objective optimization: performance assessment and algorithm design. IEEE CEC 2023 Tutorial.

5. Hypervolume Approximation for Many-objective Optimization and Learning. ECAI 2023 Tutorial.

6. Hypervolume Approximation for Many-objective Optimization and Learning. ICONIP 2023 Tutorial.

专利

尚可, 石渕久生. 飞行决策生成方法和装置、计算机设备、存储介质. 发明. 实审. 中国. 202210084970.9. 2022/1/25. 南方科技大学.

项目情况

1. 2021.01-2023.12 国家自然科学基金青年项目, 超体积指标在演化多目标优化算法中的关键问题研究, 主持

2. 2025.01-2028.12 国家自然科学基金面上项目, 进化辅助的Pareto解集学习算法及应用, 主持

3. 2025.01-2027.12 广东省自然科学基金面上项目，基于大模型的超体积子集选择算法研究，主持

4. 2019.01-2022.12 国家自然科学基金面上项目, 面向复杂Pareto前沿的动态高维多目标进化优化方法与应用, 核心成员

5. 2024.01-2027.12 国家自然科学基金面上项目, 面向子集选择的演化多模态多目标优化算法研究, 核心成员

获奖情况

2024年获得全国工业互联网创新大赛二等奖

2024年获得GECCO最佳论文奖

2022年评为IEEE高级会员

2021年获得GECCO最佳论文奖

2020年获得PPSN最佳论文提名

2019年获得CEC最佳论文奖第二名

2018年获得GECCO最佳论文奖