28th November 2023 in Brisbane, Australia

cec

Aim and Scope

Optimization is pervasive in scientific and industrial fields, such as artificial intelligence, data mining, bioinformatics, software engineering, scheduling, manufacturing, and economics. The objective functions in practical problems usually exhibit complex functional characteristics, such as multi-modality, large scale, sparsity, constraints, dynamic environment, expensive evaluation, and black box, posing challenges for traditional exact solvers. For example, the evaluation of the objective or constraint functions may involve costly physical experiments or intensive computer simulations, thereby limiting the amount of available data. Moreover, in some cases, the function evaluations can only be calculated on the basis of a large amount of data. Consequently, data-driven optimization has emerged as a powerful solution for these problems to reduce the computational cost and reshape the way we tackle complicated optimization problems, where typically machine learning techniques and optimizers are combined.

Recently, data-driven optimization has attracted increasing attention in learning-based combinatorial optimization. Combinatorial optimization tasks encompass a broad range of domains, including logistics, scheduling, transportation, and manufacturing. Traditional methods based on exact solvers and heuristic-based approaches suffer from huge computational complexity from scratch when tackling large-scale instances. With the development of graph representation learning, neural combinatorial optimization has emerged as a promising paradigm for solving classical combinatorial optimization problems. It empowers neural networks to not only handle the inherent complexity of combinatorial optimization challenges but also to learn powerful information embedded in graph representations. However, existing work on data-driven neural combinatorial optimization still has some limitations such as the dependency on high-quality data, the complexity of training and the restricted transferability among different tasks.

Topics

This workshop aims to bring together researchers from different fields working on novel theories, algorithms and applications of data-driven optimization. Topics of interest include but are not limited to:

  • Advanced surrogate models and innovative acquisition functions

  • Single-/Multi-/Many-objective data-driven large-scale optimization

  • Noisy/Robust data-driven optimization

  • Multi-task and knowledge transfer in data-driven optimization

  • Data-driven combinatorial optimization and applications

  • Graph neural networks for combinatorial optimization

  • Combination of neural networks and heuristic algorithms

Invited Speakers

  • Prof. Carlos A. Coello Coello, Department of Computer Science of CINVESTAV-IPN, Mexico City, Mexico

    Carlos A. Coello Coello (Fellow, IEEE) received the Ph.D. degree in computer science from Tulane University, New Orleans, LA, USA, in 1996. He is a Professor (CINVESTAV-3F Researcher) with the Department of Computer Science of CINVESTAV-IPN, Mexico City, Mexico. He has authored and coauthored over 570 technical papers and book chapters. He has also co-authored the book Evolutionary Algorithms for Solving Multi-Objective Problems (Second Edition, Springer, 2007). His publications currently report over 69,790 citations in Google Scholar (his H-index is 102). His research interests include evolutionary multiobjective optimization and constraint-handling techniques for evolutionary algorithms. Dr. Coello Coello was a recipient of the 2007 National Research Award from the Mexican Academy of Sciences in the area of Exact Sciences, the 2013 IEEE Kiyo Tomiyasu Award, the 2012 National Medal of Science and Arts in the area of Physical, Mathematical and Natural Sciences and the 2021 IEEE Computational Intelligence Society Evolutionary Computation Pioneer Award. He is currently the Editor-in-Chief of the IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION. He is a member of the Association for Computing Machinery and the Mexican Academy of Science.

  • Prof. Xiaodong Li, Royal Melbourne Institute of Technology(RMIT), Australia

    Xiaodong Li (Fellow, IEEE) received the B.Sc. degree from Xidian University, Xi’an, China, in 1988, and the Ph.D. degree in information science from the University of Otago, Dunedin, New Zealand, in 1998. He is a Professor with the School of Computing Technologies, RMIT University, Melbourne, VIC, Australia. His research interests include machine learning, evolutionary computation, neural networks, data analytics, multiobjective optimization, multimodal optimization, and swarm intelligence. Prof. Li was a recipient of the 2013 ACM SIGEVO Impact Award and the 2017 IEEE CIS IEEE Transactions on Evolutionary Computation Outstanding Paper Award. He serves as an Associate Editor for the IEEE Transactions on Evolutionary Computation and Swarm Intelligence (Springer). He is the Former Vice-Chair of the IEEE Task Force on Multimodal Optimization and the Former Chair of the IEEE CIS Task Force on Large Scale Global Optimization.

  • Dr. Ying Bi, Zhengzhou University, China

    Ying Bi (Member, IEEE) received the Ph.D. degree from the Victoria University of Wellington, Wellington, New Zealand, in 2020. She is a distinguished professor, selected by National Young Talent Program, with the computational intelligence laboratory of Zhengzhou University. She has been engaged in theoretical and applied research in genetic programming, evolutionary computing, machine learning, computer vision and other fields for a long time, published the world's first English monograph on image classification based on genetic programming, published 55 academic papers in international academic journals and conferences, including 25 SCI journal articles, published 16 papers as the first or corresponding author of TOP journals of the first region of the Chinese Academy of Sciences.

  • Dr. Ye Tian, Anhui University, China

    Ye Tian is currently an Associate Professor with the School of Computer Science and Technology, Anhui University, Hefei, China. His research interests include evolutionary computation and its applications, and has published more than 60 papers with 7000+ citations. He is the recipient of the 2022 IEEE CIS Outstanding PhD Dissertation Award, the 2018, 2021, and 2024 IEEE TEVC Outstanding Paper Awards, and the 2020 IEEE CIM Outstanding Paper Award.

  • Dr. Cheng He, Huazhong University of Science and Technology, China

    Cheng He received the Ph.D. degree from the Huazhong University of Science and Technology, Wuhan, China, in 2018. 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.). He is an Associate Editor of Complex & Intelligent Systems, and an Editorial Board member of Electronics.

  • Mr. Jan Tönshoff, RWTH Aachen University, Germany

    Jan Tönshoff is a PhD student at the Chair for Logic and Theory of Discrete Systems at RWTH Aachen University, where he works for Prof. Martin Grohe. His research explores both practical and theoretical aspects of machine learning on graph-structured data, with applications ranging from combinatorial optimization to learning on relational databases. One of his core research interest is to develop trainable heuristics for Constraint Satisfaction Problems based on Graph Neural Networks and Reinforcement Learning.

Organization & Schedule

This half-day workshop will consist of two invited speeches (30 minutes each), six regular oral presentations (15 minutes each + 5 minutes discussion), and a 10-minute conclusion session. The free discussion will provide the opportunity for all participants to ask questions and engage in an interactive discussion with the expert, focusing on identifying key challenges, potential collaborations, and future research directions in the field. After the discussion, the workshop organizers will summarize the key takeaways from the workshop, highlighting important insights, research trends, and potential opportunities that emerged during the discussions. Details of the conference can be obtained by AJCAI2023 website https://ajcai2023.org/index.html.

Speaker Australian Eastern Time (GMT+10)
Introduction 9:00-9:10
Prof. Carlos A. Coello Coello 9:10-9:40
Prof. Xiaodong Li 9:45-10:15
Jan Tönshoff 10:20-10:35
Shiqing Liu 10:40-10:55
Xiangyu Wang 11:00-11:15
Dr. Ye Tian 11:20-11:35
Dr. Ying Bi 11:40-11:55
Dr. Cheng He 12:00-12:20
Conclusion 12:20-12:30

Organizers

Dr. Xilu Wang, Faculty of Technology, Bielefeld University, Germany. Email: xilu.wang@uni-bielefeld.de

Shiqing Liu, Faculty of Technology, Bielefeld University, Germany. Email: shiqing.liu@uni-bielefeld.de

Xiangyu Wang, Faculty of Technology, Bielefeld University, Germany. Email: xiangyu.wang@uni-bielefeld.de

Dr. Chen Wang, Department of HPC and Data Science, National Institute of Water and Atmospheric Research, New Zealand. Email: Chen.Wang@niwa.co.nz

Prof. Dr. Yaochu Jin, Westlake University, China. Email: jinyaochu@westlake.edu.cn

Biography of the Organizers

Dr. Xilu Wang is currently a postdoc in Nature Inspired Computing and Engineering (NICE) group, faculty of technology, Bielefeld University, Germany. She obtained her PhD. in 2022, with a thesis on “Bayesian Evolutionary Optimization for Heterogeneously Expensive Multi-objective Problems”. She has been involved in research since 2018 and published more than 10 papers in international journals and conferences. Her current research lines are Bayesian optimization, federated optimization, transfer learning, surrogate modelling and computational intelligence.

Shiqing Liu is currently a Ph.D. student in the faculty of technology, Bielefeld University, Germany. She received the B.Sc. degree in automation and the M.Sc. degree in control science and engineering from Beijing Institute of Technology, Beijing, China in 2017 and 2020 respectively. Her current research interests include neural combinatorial optimization, graph neural networks, federated learning and neural architecture search. She received the Best Student Paper Award at DOCS2023 and the Outstanding Presentation Award at ABCP2023. She is currently a graduate student member of IEEE.

Xiangyu Wang is currently a Ph.D. student in the faculty of technology, Bielefeld University, Germany. She received a B.Sc. degree and an M.Sc. degree in mathematics and applied mathematics from China University of Petroleum, Qingdao, Shandong, China, in 2020 and 2022, respectively. Her current research interests include graph neural networks, evolutionary algorithms, and statistical methods in metabolomics. She has been in charge of two projects as a project leader.

Chen Wang received his PhD degree in Engineering from Victoria University of Wellington, Wellington, New Zealand (2020). He is currently a data scientist from the National Institute of Water and Atmospheric Research, the largest Crown Research Institute in New Zealand. He also holds an Adjunct Research Fellow position at Victoria University of Wellington, New Zealand. His research mainly focuses on utilising combinatorial optimisation and reinforcement learning techniques in solving challenging scientific problems in the climate, fresh water and marine science fields.

Prof. Dr. Yaochu Jin received the B.Sc., M.Sc., and Ph.D. degrees from Zhejiang University, Hangzhou, China in 1988, 1990 and 1996, respectively, and the Dr.-Ing. degree from Ruhr University Bochum, Germany in 2001. He is currently an Alexander von Humboldt Professor for AI and Head of the Nature-Inspired Computing and Engineering (NICE) Group, Faculty of Technology, Bielefeld University, Germany. His research interests include computational approaches to understanding evolution, learning and development in biology, and biological approaches to solving complex engineering problems. He was the Program Chair of the 2013 IEEE Congress on Evolutionary Computation, Conference Chair of the 2020 IEEE Congress on Evolutionary Computation, and General Co-Chair of the 2016 IEEE Symposium Series on Computational Intelligence. Prof. Jin is an Associate Editor the IEEE Transactions on Evolutionary Computation and IEEE Transactions on Cybernetics. He has given plenary / keynote talks on over 50 international conferences on various topics, including data-driven optimization, federated learning and optimization, morphogenetic robotics, and multi-objective machine learning. He is a Member of Academia Europaea and Fellow of IEEE.