Evolutionary Computation Technical Committee

Task Force on

Evolutionary Learning

More Info

Mission

The intersection of evolutionary computation and machine learning has been receiving more and more attentions. On one hand, evolutionary computation methods can be applied to solve complicated optimization problems in machine learning, which have led to many encouraging outcomes, e.g., in neural architecture search, optimization of high-quality and diverse policies (known as quality-diversity) for reinforcement learning, and selection of a subset of individual learners for ensemble pruning. On the other hand, machine learning can be used to help configure and accelerate evolutionary computation methods, e.g., the use of reinforcement learning for dynamic algorithm configuration and the use of learning models for acquisition of good data points. We believe that the integration of evolutionary computation and machine learning will play a critical role in solving complex real-world tasks.

Aim 1

To further explore the intersection between evolutionary computation and machine learning, generating state-of-the-art theory, methods and applications of evolutionary learning.

img

Aim 2

To promote discussions and connections for researchers from evolutionary computation and machine learning. Note that the researchers from these two fields often attend the conferences in their own fields, e.g., IEEE CEC/ACM GECCO for evolutionary computation and AAAI/IJCAI/ICML/NeurIPS for machine learning.

img

Aim 3

To promote the generation of new search lines in evolutionary learning.

img

Scope

The scope of this task force includes (but is not limited to) the following topics:

Evolutionary Supervised Learning

Evolutionary Unsupervised Learning

Evolutionary Semi-supervised Learning

Evolutionary Reinforcement Learning

Evolutionary Ensembel Learning

(Dynamic) Algorithm Configuration by Learning

Acceleration of Evolutionary Optimization by Learning

Bayesian Optimziation

Learning to Optimize

Theory of Evolutionary Learning

Real-world Applications of Evolutionary Learning

Events

  • 2025/06/08-2025/06/12 IEEE CEC 2025: Special Session on Evolutionary Learning and Learning to Optimize. Session Chairs: Peng Yang, Josu Ceberio, and Chao Qian [link]
    2024/06/30-2024/07/05 IEEE WCCI 2024: Special Session on Evolutionary Learning and Learning to Optimize. Session Chairs: Peng Yang, Josu Ceberio, and Chao Qian [link]
    2024/06/30-2024/07/05 IEEE WCCI 2024: Tutorial of "Pareto Optimization for Subset Selection: Theories and Practical Algorithms", Speakers: Chao Qian

Chairs

img

Chao Qian

Chair

He is an Associate Professor in the School of Artificial Intelligence, Nanjing University, China. He received the BSc and PhD degrees in the Department of Computer Science and Technology from Nanjing University. After finishing his PhD in 2015, he became an Associate Researcher in the School of Computer Science and Technology, University of Science and Technology of China, until 2019, when he returned to Nanjing University.

His research interests include artificial intelligence, evolutionary computation and machine learning. He has published one book “Evolutionary Learning: Advances in Theories and Algorithms”, and over 50 papers in top-tier journals (AIJ, ECJ, TEvC, Algorithmica, TCS) and conferences (AAAI, IJCAI, NeurIPS, ICLR). He has won the ACM GECCO 2011 Best Theory Paper Award, the IDEAL 2016 Best Paper Award, and the IEEE CEC 2021 Best Student Paper Award Nomination. He is an associate editor of IEEE Transactions on Evolutionary Computation, a young associate editor of Science China Information Sciences, an editorial board member of the Memetic Computing journal, and was a guest editor of Theoretical Computer Science. He is a member of IEEE Computational Intelligence Society (CIS) Evolutionary Computation Technical Committee, the founding chair of IEEE CIS Task Force on Evolutionary Learning, and was also the chair of IEEE CIS Task Force on Theoretical Foundations of Bio-inspired Computation. He has regularly given tutorials and co-chaired special sessions at leading evolutionary computation conferences (CEC, GECCO, PPSN), and has been invited to give an Early Career Spotlight Talk "Towards Theoretically Grounded Evolutionary Learning" at IJCAI 2022. He will be a Program Co-Chair of PRICAI 2025. He is a recipient of the National Science Foundation for Excellent Young Scholars (2020), and CCF-IEEE CS Young Computer Scientist Award (2023).

img

Peng Yang

Vice-Chair

He is a tenure-track assistant professor jointly in the Department of Statistics and Data Science and the Department of Computer Science and Engineering, Southern University of Science and Technology (SUSTech), China. He received his B.Sc. and Ph.D. degrees in the Department of Computer Science and Technology from University of Science and Technology of China in 2012 and 2017, respectively. From 2017 to 2018, he was a Senior Engineer in Huawei and then he joined SUSTech. His research interests include Evolutionary Computation, Reinforcement Learning, and Complex System Identification. He has published 38 papers in top journals and conferences like TEVC, TCYB, JSAC, TNNLS, TKDE, TASE and NeurIPS. He has also been authorized with 12 invention patents by China, USA, and Germany. He has served as the reviewer for top-tier journals (TEVC, TNNLS, TIE) and the PC member of top conferences (NeurIPS, ICLR, and ICML). He is a member of IEEE Computational Intelligence Society (CIS) Evolutionary Computation Technical Committee. He is an IEEE Senior Member.

img

Josu Ceberio

Vice-Chair

He is associate professor in the Department of Computer Science and Artificial Intelligence at the University of the Basque Country UPV/EHU. Since 2010, he has been a member of the Intelligent Systems Group where he obtained, in 2014, the Ph.D. in Computer Science. Most of his contributions have been in the field of estimation of distribution algorithms and combinatorial optimization, however, he has recently focused his research to the development of metaheuristic algorithms that incorporate reinforcement learning techniques to efficiently approach combinatorial optimization problems. Overall, Josu has published more than 54 research works in journals and international conferences in the area. He has also acted as a reviewer for more than 15 prestigious journals such as IEEE Trans. Computational Intelligence Magazine, IEEE Trans. Cybernetics and IEEE Trans. on Evo. Comp, and since 2022 is Associate Editor of the IEEE Trans. On Evolutionary Computation. Finally, it is worth mentioning having actively participated in organizing scientific events, the most notable being having acted as Proceedings Chair in the 2017 IEEE CEC, and in the 2020 ACM GECCO. He has also organized special session and workshops in IEEE CEC (2017, 2018, 2021) and ACM GECCO (2019, 2020) related to Evolutionary Computation for Permutation Problems. Currently, he is member of the IEEE CIS Taskforce on Evolutionary Scheduling and Combinatorial Optimization.

Members

Aiming Zhou

East China Normal University

China

Bing Xue

Victoria University of Wellington

New Zealand

Carola Doerr

Sorbonne Université

France

Chong Liu

University of Chicago

USA

Dan-Xuan Liu

Nanjing University

China

Ekhine Irurozki

Télécom Paris

France

Hong Qian

East China Normal University

China

Jialin Liu

Southern University of Science and Technology

China

Jose Lozano

University of the Basque Country

Spain

Kai Qin

Swinburne University of Technology

Australia

Ke Tang

Southern University of Science and Technology

China

Ke Xue

Nanjing University

China

Liang Feng

Chongqing University

China

Mario F. Pavone

University of Catania

Italy

Markus Wagner

Monash University

Australia

Miqing Li

University of Birmingham

UK

Shengcai Liu

Agency for Science, Technology and Research (A*STAR)

Singapore

Xiaodong Li

RMIT University

Australia

Yanan Sun

Sichuan University

China

Yang Yu

Nanjing University

China

Yi Mei

Victoria University of Wellington

New Zealand

Yue Wu

Xidian University

China