Zefeng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zefeng Chen has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Yuren Zhou
School of Software Engineering, Sun Yat-sen University, Zhuhai, China
20 shared publications - Yi Xiang
South China University of Technology
9 shared publications - Xiaoyu He
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
8 shared publications - Zhengxin Huang
Department of Computer Science, Youjiang Medical University for Nationalities, Baise 533000, China
6 shared publications - Yew-Soon Ong
Nanyang Technological University
5 shared publications Yuren Zhou
5 shared publications
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 130-146
Towards Feature Selection in High-Dimensional Data: A Multi-task Evolution Strategy Aided with Symmetrical Uncertainty and Attention
- 2 September 2026
- Published by Springer Nature
- p. 130-146
Towards Feature Selection in High-Dimensional Data: A Multi-task Evolution Strategy Aided with Symmetrical Uncertainty and Attention
- 3 April 2026
- Published by MIT Press in Evolutionary Computation
- Vol. 34 (3) , 1-33
Runtime Analysis of Typical Decomposition Approaches in MOEA/D for Many-Objective Optimization Problems
Decomposition-based multiobjective evolutionary algorithms (MOEAs) are popular methods utilized to address many-objective optimization problems (MaOPs). These algorithms decompose the original MaOP into several scalar optimization subproblems, and solve them to obtain a set of solutions to approximate the Pareto front (PF). The decomposition approach is an important component in them. This paper presents a runtime analysis of a MOEA based on the classic decomposition framework using the typical weighted sum (WS), Tchebycheff (TCH), and penalty-based boundary intersection (PBI) approaches to obtain an optimal solution for any subproblem of two pseudo-Boolean benchmark MaOPs, namely mLOTZ and mCOCZ. Due to the complexity and limitation of the theoretical analysis techniques, the analyzed algorithm employs 1-bit mutation to generate offspring individuals. The results indicate that when using WS, the analyzed algorithm can consistently find an optimal solution for every subproblem, which is located in the PF, in polynomial expected runtime. In contrast, the algorithm requires at least exponential expected runtime (with respect to the number of objectives m) for certain subproblems when using TCH or PBI, even though the landscapes of all objective functions in the two benchmarks are strictly monotone. Moreover, this analysis reveals a drawback of using WS: the optimal solutions obtained by solving subproblems are more easily mapped to the same point in the PF, compared to the case of using TCH. When using PBI, a smaller value of the penalty parameter is a good choice for faster convergence to the PF but may compromise diversity. To further understand the impact of these approaches in practical algorithms, numerical experiments on using bit-wise mutation to generate offspring individuals are conducted. The findings of this study may be helpful for designing more efficient decomposition approaches for MOEAs in future research.
- 3 April 2026
- Published by MIT Press in Evolutionary Computation
- Vol. 34 (3) , 1-33
Runtime Analysis of Typical Decomposition Approaches in MOEA/D for Many-Objective Optimization Problems
Decomposition-based multiobjective evolutionary algorithms (MOEAs) are popular methods utilized to address many-objective optimization problems (MaOPs). These algorithms decompose the original MaOP into several scalar optimization subproblems, and solve them to obtain a set of solutions to approximate the Pareto front (PF). The decomposition approach is an important component in them. This paper presents a runtime analysis of a MOEA based on the classic decomposition framework using the typical weighted sum (WS), Tchebycheff (TCH), and penalty-based boundary intersection (PBI) approaches to obtain an optimal solution for any subproblem of two pseudo-Boolean benchmark MaOPs, namely mLOTZ and mCOCZ. Due to the complexity and limitation of the theoretical analysis techniques, the analyzed algorithm employs 1-bit mutation to generate offspring individuals. The results indicate that when using WS, the analyzed algorithm can consistently find an optimal solution for every subproblem, which is located in the PF, in polynomial expected runtime. In contrast, the algorithm requires at least exponential expected runtime (with respect to the number of objectives m) for certain subproblems when using TCH or PBI, even though the landscapes of all objective functions in the two benchmarks are strictly monotone. Moreover, this analysis reveals a drawback of using WS: the optimal solutions obtained by solving subproblems are more easily mapped to the same point in the PF, compared to the case of using TCH. When using PBI, a smaller value of the penalty parameter is a good choice for faster convergence to the PF but may compromise diversity. To further understand the impact of these approaches in practical algorithms, numerical experiments on using bit-wise mutation to generate offspring individuals are conducted. The findings of this study may be helpful for designing more efficient decomposition approaches for MOEAs in future research.
- 7 September 2024
- Published by Springer Nature
- p. 369-385
Pareto-Informed Multi-objective Neural Architecture Search
- 7 September 2024
- Published by Springer Nature
- p. 369-385
Pareto-Informed Multi-objective Neural Architecture Search
- 15 November 2023
- Published by Springer Nature
- p. 482-493
Towards Scalable Feature Selection: An Evolutionary Multitask Algorithm Assisted by Transfer Learning Based Co-surrogate
- 15 November 2023
- Published by Springer Nature
- p. 482-493
Towards Scalable Feature Selection: An Evolutionary Multitask Algorithm Assisted by Transfer Learning Based Co-surrogate
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 15 (3) , 1474-1486
Multitask Neuroevolution for Reinforcement Learning With Long and Short Episodes
Studies have shown evolution strategies (ES) to be a promising approach for reinforcement learning (RL) with deep neural networks. However, the issue of high sample complexity persists in applications of ES to deep RL over long horizons. This paper is the first to address the shortcoming of todays methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand. The auxiliary tasks, extracted from the target, allow an agent to update and quickly evaluate policies on shorter time horizons. The evolved skills are then transferred to guide the longer and harder task towards an optimal policy. We demonstrate that the NuEMT algorithm achieves data-efficient evolutionary RL, reducing expensive agent-environment interaction data requirements. Our key algorithmic contribution in this setting is to introduce, for the first time, a multitask skills transfer mechanism based on the statistical importance sampling technique. In addition, an adaptive resource allocation strategy is utilized to assign computational resources to auxiliary tasks based on their gleaned usefulness. Experiments on a range of continuous control tasks from the OpenAI Gym confirm that our proposed algorithm is efficient compared to recent ES baselines.
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 15 (3) , 1474-1486
Multitask Neuroevolution for Reinforcement Learning With Long and Short Episodes
Studies have shown evolution strategies (ES) to be a promising approach for reinforcement learning (RL) with deep neural networks. However, the issue of high sample complexity persists in applications of ES to deep RL over long horizons. This paper is the first to address the shortcoming of todays methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand. The auxiliary tasks, extracted from the target, allow an agent to update and quickly evaluate policies on shorter time horizons. The evolved skills are then transferred to guide the longer and harder task towards an optimal policy. We demonstrate that the NuEMT algorithm achieves data-efficient evolutionary RL, reducing expensive agent-environment interaction data requirements. Our key algorithmic contribution in this setting is to introduce, for the first time, a multitask skills transfer mechanism based on the statistical importance sampling technique. In addition, an adaptive resource allocation strategy is utilized to assign computational resources to auxiliary tasks based on their gleaned usefulness. Experiments on a range of continuous control tasks from the OpenAI Gym confirm that our proposed algorithm is efficient compared to recent ES baselines.
- Open Access
Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes
Studies have shown evolution strategies (ES) to be a promising approach for reinforcement learning (RL) with deep neural networks. However, the issue of high sample complexity persists in applications of ES to deep RL over long horizons. This paper is the first to address the shortcoming of today's methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand. The auxiliary tasks, extracted from the target, allow an agent to update and quickly evaluate policies on shorter time horizons. The evolved skills are then transferred to guide the longer and harder task towards an optimal policy. We demonstrate that the NuEMT algorithm achieves data-efficient evolutionary RL, reducing expensive agent-environment interaction data requirements. Our key algorithmic contribution in this setting is to introduce, for the first time, a multitask skills transfer mechanism based on the statistical importance sampling technique. In addition, an adaptive resource allocation strategy is utilized to assign computational resources to auxiliary tasks based on their gleaned usefulness. Experiments on a range of continuous control tasks from the OpenAI Gym confirm that our proposed algorithm is efficient compared to recent ES baselines.
Open AccessMultitask Neuroevolution for Reinforcement Learning with Long and Short Episodes
Studies have shown evolution strategies (ES) to be a promising approach for reinforcement learning (RL) with deep neural networks. However, the issue of high sample complexity persists in applications of ES to deep RL over long horizons. This paper is the first to address the shortcoming of today's methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand. The auxiliary tasks, extracted from the target, allow an agent to update and quickly evaluate policies on shorter time horizons. The evolved skills are then transferred to guide the longer and harder task towards an optimal policy. We demonstrate that the NuEMT algorithm achieves data-efficient evolutionary RL, reducing expensive agent-environment interaction data requirements. Our key algorithmic contribution in this setting is to introduce, for the first time, a multitask skills transfer mechanism based on the statistical importance sampling technique. In addition, an adaptive resource allocation strategy is utilized to assign computational resources to auxiliary tasks based on their gleaned usefulness. Experiments on a range of continuous control tasks from the OpenAI Gym confirm that our proposed algorithm is efficient compared to recent ES baselines.
- 9 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (2) , 1294-1307
Scaling Multiobjective Evolution to Large Data With Minions: A Bayes-Informed Multitask Approach
In an era of pervasive digitalization, the growing volume and variety of data streams poses a new challenge to the efficient running of data-driven optimization algorithms. Targeting scalable multiobjective evolution under large-instance data, this article proposes the general idea of using subsampled small-data tasks as helpful minions (i.e., auxiliary source tasks) to quickly optimize for large datasets—via an evolutionary multitasking framework. Within this framework, a novel computational resource allocation strategy is designed to enable the effective utilization of the minions while guarding against harmful negative transfers. To this end, an intertask empirical correlation measure is defined and approximated via Bayes’ rule, which is then used to allocate resources online in proportion to the inferred degree of source–target correlation. In the experiments, the performance of the proposed algorithm is verified on: 1) sample average approximations of benchmark multiobjective optimization problems under uncertainty and 2) practical multiobjective hyperparameter tuning of deep neural network models. The results show that the proposed algorithm can obtain up to about 73% speedup relative to existing approaches, demonstrating its ability to efficiently tackle real-world multiobjective optimization involving evaluations on large datasets.
- 9 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (2) , 1294-1307
Scaling Multiobjective Evolution to Large Data With Minions: A Bayes-Informed Multitask Approach
In an era of pervasive digitalization, the growing volume and variety of data streams poses a new challenge to the efficient running of data-driven optimization algorithms. Targeting scalable multiobjective evolution under large-instance data, this article proposes the general idea of using subsampled small-data tasks as helpful minions (i.e., auxiliary source tasks) to quickly optimize for large datasets—via an evolutionary multitasking framework. Within this framework, a novel computational resource allocation strategy is designed to enable the effective utilization of the minions while guarding against harmful negative transfers. To this end, an intertask empirical correlation measure is defined and approximated via Bayes’ rule, which is then used to allocate resources online in proportion to the inferred degree of source–target correlation. In the experiments, the performance of the proposed algorithm is verified on: 1) sample average approximations of benchmark multiobjective optimization problems under uncertainty and 2) practical multiobjective hyperparameter tuning of deep neural network models. The results show that the proposed algorithm can obtain up to about 73% speedup relative to existing approaches, demonstrating its ability to efficiently tackle real-world multiobjective optimization involving evaluations on large datasets.