July 2-5, 2023 Swissôtel Chicago
Aim and Scope
Optimization problems are ubiquitous in the real-world, including science, engineering, and technology. Despite a proliferation of studies on optimization, most existing optimization methods rely on a traditional centralized mode. Recently, the growing storage and computational power of edge devices of modern distributed networks have motivated the development of decentralized computing, such as federated optimization. The use of a wealth of data collected by edge devices raises the concern of privacy leakage and security threats, posing challenges to traditional centralized optimization methods. In addition, in some scenarios, users care about not only the optimization performance, but also fairness in decision-making, multi-objective preference, or model construction. Therefore, the development of new algorithmic ideas and theories in optimization paradigm is crucial.
Driven by the aforementioned scenarios, developing secure, privacy-preserving, and fairness-aware optimization techniques has attracted increasing attention most recently. Related research topics include security and robustness, privacy-preservation, fairness, verifiability, and transparency in designing optimization algorithms and many questions remain open. First of all, it is worth discussing the definitions of security, privacy, and fairness in the context of optimization, as many of these concepts remain elusive. Second, a key challenge is to achieve an appropriate balance between the optimization performance and privacy/security/fairness guarantees. Third, longstanding questions in distributed and federated machine learning must be revisited in the context of optimization, such as non-IID data and communication efficiency. Last but not the least, it is desired to design new test benchmark problems and performance indicators for the evaluation of secure, privacy-preserving, and fairness-aware optimization methods.
The aim of this special session is to bring together researchers from different application fields working on optimization and present new solutions to the above-discussed challenges. The special session will focus on new advances, review and discuss the state-of-the-art in the theory, algorithm design, and applications of using secure, privacy-preserving, and fairness-aware solutions in optimization.
Authors are invited to submit papers on one or more of the following topics
• Privacy-preserving Bayesian optimization
• Privacy-preserving evolutionary algorithm
• Privacy-preserving distributed optimization
• Secure federated data-driven optimization
• Federated surrogate models
• Fairness-aware acquisition function
• Attacks and defenses in optimization
• Fairness-aware multi-objective optimization
• Fairness-aware data-driven optimization
• Fairness-aware federated optimization
• Fairness-aware multi-objective machine learning
• Benchmark problems for secure, privacy-preserving and fairness-aware optimization
• Performance indicators for secure, privacy-preserving and fairness-aware optimization
Please follow the submission guideline from the CEC 2023 Submission Website https://2023.ieee-cec.org/paper-submission/. Special session papers are treated the same as regular conference papers. Please specify that your paper is for the Special Session on Secure, Privacy-Preserving, and Fairness-Aware Optimization. All papers accepted and presented at CEC 2023 will be included in the conference proceedings published by IEEE Explore, which are typically indexed by EI.
Paper Submission: January 13th, 2023
Paper Reviews: March 3rd, 2023
Paper Re-submissions: March 24th, 2023
Paper Final Notifications: March 31st, 2023
Print-Ready Manuscripts: April 15th, 2023
Dr Qiqi Liu, NICE, Faculty of Technology, Bielefeld University, Germany. Email: email@example.com
Dr Guo Yu, Institute of Intelligent Manufacturing, Nanjing Tech University, Nanjing, 211816, China and School of Information Science and Engineering East China University of Science and Technology, Shanghai 200237, China. Email: firstname.lastname@example.org
Dr Xilu Wang, NICE, Faculty of Technology, Bielefeld University, Germany. Email: email@example.com
Ms Yuping Yan (Ph.D. candidate), Department of Informticas, Eötvös Loránd University, Hungary. Email: firstname.lastname@example.org
Prof Yaochu Jin, NICE, Faculty of Technology, Bielefeld University, Germany. Email: email@example.com
Biography of the Organizers
Qiqi Liu is currently a research scientist at the Bielefeld university. She received her PhD from University of Surrey in 2022, with a thesis on “Evolutionary optimization of many-objective problems with irregular Pareto fronts”. She has been involved in research since 2013 and published more than 15 papers in international journals and conferences. Her current research lines are multi-objective evolutionary optimization, data-driven evolutionary optimization, privacy-preserving Bayesian optimization, and federated data-driven optimization. She is a regular reviewer of the IEEE Transactions on Evolutionary Computation, Swarm and Evolutionary Computation, IEEE Transactions on Artificial Intelligence, and Complex & Intelligent Systems.
Guo Yu received the B.S. degree in information and computing science and the M.Eng. degree in computer technology from Xiangtan University, Xiangtan, China, in 2012 and 2015, respectively. He received the Ph.D. degree in computer science from University of Surrey, Guildford, U.K., in 2020. He is currently a research fellow with the Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology. His current research interests include computational intelligence and machine learning. He has authored more than 20 referred papers including those published in IEEE Transaction on Evolutionary Computation, and IEEE Transaction on Cybernetics. He serves as a Guest Editor of Symmetry and a regular reviewer of more than 10 journals such as the IEEE TEVC, and IEEE TCYB.
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 about 10 papers in international journals and conferences. Her current research lines are Bayesian optimization, federated optimization, transfer learning, surrogate modelling and computational intelligence.
Yuping Yan is currently a Ph.D. candidate in the Faculty of Algebra, Eötvös Loránd University, Hungary. She got her double master’s degrees from the University of Trento (Italy) and Eötvös Loránd University in cyber security major. She works in the board areas of identity management, authentication, cloud computing, and federated learning. Her current research focuses on attribute-based encryption, formal protocol verification schemes, and privacy-preserving federated learning frameworks on the medical hearth. During her four years of Ph.D., she published some pioneered results and more than 10 papers on top conferences and journals and won the “best paper award” in the IEEE International Conference on Computing, Electronics & Communications Engineering 2020 (IEEE iCCECE ‘20).
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.