Meet: Yaochu Jin, AdCom Member of IEEE CIS
What is your title, and place of work? (or Technical Field of Research)?
I am an Alexander von Humboldt Professor for Artificial Intelligence endowed by the German Federal Ministry of Education and Research, with the Chair of Nature Inspired Computing and Engineering, Faculty of Technology, Bielefeld, Germany. I am also a part-time Distinguished Chair in Computational Intelligence, Department of Computer Science, University of Surrey, United Kingdom. Most recently, I was also elected to be a Member of Academia Europaea.
How long have you been a member of CIS and what was the reason you chose to join IEEE CIS?
I joined IEEE in 1998 when I attended the 1998 IEEE World Congress on Computational Intelligence (WCCI) held in Alaska. I selected a few IEEE Societies relevant to my research area, including the Neural Network Council, which is the predecessor of IEEE CIS. Over the years, CIS has become my “home” Society of IEEE, not only because CIS fits my research interest the best but also because I always felt at home when I attended the CIS events such as WCCI.
What Computational Intelligence society committee do you serve?
I have been involved in many volunteer roles in CIS, starting from the founding chair of the Task Force on Evolutionary Computation in Dynamic and Uncertain Environments of the Evolutionary Computation Technical Committee in 2004. Then I served as a member of the several technical committees and the award subcommittee. During 2009-2020 I was the Chair of the Continuing Education and Industrial Liaison Sub-Committees. In 2011, I became the Chair of the Intelligent Systems Applications Technical Committee. I was elected to be an AdCom member in 2013-2014 and then served as the Vice President for Technical Committee in 2014-2015, before I took over the Editor-in-Chief of the IEEE Transactions on Cognitive and Developmental Systems in 2016. Presently, I am a member of the AdCom of CIS.
I was also an IEEE CIS Distinguished Lecturer during 2012-2014 and 2017-2019.
What have you learned from your experience and how has it helped you professionally?
Being an active volunteer in CIS has been very helpful in my career development and personal life. By participating in various task forces or committees, I had the opportunity to know many leading researchers in the CIS. I learned a lot from their way of doing research, got inspiration and encouragement from discussions with them, and benefited from strong professional support in career development over the past decades. In addition, I also gained experience in organizing events and research projects by chairing technical committees in CIS. Finally, many colleagues in the CIS became a good friend of me.
What has been the most fun/rewarding thing about being a volunteer for the IEEE Computational Intelligence Society? What have you enjoyed the most?
Making new friends and meeting with old friends in CIS has been the most enjoyable part of being active volunteer of CIS. I enjoyed discussing various businesses at the CIS meetings, having a casual chat with the friends, or going for a beer in the evening. I liked most travelling to a new place for a CIS meeting, where I would never have been otherwise.
Tell us something about you that we don’t know.
Recently I became interested in privacy-preserving learning and optimization, especially in the use of multi-objective evolutionary algorithms for federated learning, and evolutionary federated neural architecture search, and federated data-driven optimization. We are preparing a book on Federated Learning, which is planned to appear sometime in 2022.
IEEE Fellow is a distinction reserved for select IEEE members whose extraordinary accomplishments in any of the IEEE fields of interest are deemed fitting of this prestigious grade elevation. The deadline for IEEE Fellow Nominations is 1 March 2022. 
Constrained optimization problems (COPs) are frequently encountered in real-world design applications. For some COPs, the evaluation of the objective(s) and/or constraint(s) may involve significant computational/temporal/financial cost. Such problems are referred to as expensive COPs (ECOPs). Surrogate modeling has been widely used in conjunction with optimization methods for such problems, wherein the search is partially driven by an approximate function instead of true expensive evaluations. However, for any true evaluation, nearly all existing methods compute all objective and constraint values together as one batch. Such full evaluation approaches may be inefficient for cases where the objective/constraint(s) can be evaluated independently of each other. In this article, we propose and study a constraint handling strategy for ECOPs using partial evaluations.
This article presents a novel variational model based on fuzzy clustering and total variation regularization for superpixel segmentation. Compared with the classical hard-labeled methodologies, our approach gives soft results via the fuzzy membership function, and moreover, the use of total variation provides additional information that can enhance the superpixel regularity, which in turn improves the segmentation performance. To efficiently minimize the energy functional of the proposed model, we adopt an alternating direction method of multipliers with the modified Chambolle’s fast duality projection algorithm. Our algorithm can generate regular and compact superpixels with high segmentation accuracy, satisfactory boundary adherence, and low computational cost. Comparative experimental results with the current state-of-the-art approaches reveal the superior performance of the proposed method. 
