Population-based meta-heuristic algorithms such as Evolutionary Algorithms (EAs) in their original forms are usually designed for locating a single global solution. These algorithms typically converge to a single solution because of the global selection scheme used. Nevertheless, many real-world problems are “multimodal” by nature, i.e., multiple satisfactory solutions exist. It may be desirable to locate many such satisfactory solutions so that a decision maker can choose one that is most proper in his/her problem domain. Numerous techniques have been developed in the past for locating multiple optima (global or local). These techniques are commonly referred to as “niching” methods. A niching method can be incorporated into a standard EA to promote and maintain formation of multiple stable subpopulations within a single population, with an aim to locate multiple globally optimal or suboptimal solutions. Many niching methods have been developed in the past, including crowding, fitness sharing, derating, restricted tournament selection, clearing, speciation, etc.
Most of existing niching methods, however, have difficulties which need to be overcome before they can be applied successfully to real-world multimodal problems. Some identified issues include: difficulties to pre-specify some niching parameters; difficulties in maintaining found solutions in a run; extra computational overhead; poor scalability when dimensionality is high. This special session aims to highlight the latest developments in niching methods, bring together researchers from academia and industries, and explore future research directions on this topic. We invite authors to submit original and unpublished work on niching methods. Topics of interest include but are not limited to:
- Theoretical developments in multimodal optimization
- Niching methods that incurs lower computational costs
- Handling the issue of niching parameters in niching methods
- Handling the scalability issue in niching methods
- Handling problems characterized by massive multi-modality
- Adaptive or parameter-less niching methods
- Multiobjective approaches to niching
- Multimodal optimization in dynamic environments
- Niching methods applied to discrete multimodal optimization problems
- Niching methods applied to constrained multimodal optimization problems
- Niching methods using parallel or distributed computing techniques
- Benchmarking niching methods, including test problem design and performance metrics
- Comparative studies of various niching methods
- Niching methods applied to engineering and other real-world multimodal optimization problems
Please note that we are NOT interested if the adopted task is to find
a single solution of a multimodal problem.
Furthermore, a companion Competition on Niching Methods for Multimodal Optimization will be organized in conjunction with this special session. The aim of the competition is to provide a common platform that encourages fair and easy comparisons across different niching algorithms. The competition allows participants to run their own niching algorithms on 20 benchmark multimodal functions with different characteristics and levels of difficulty. Researchers are welcome to evaluate their niching algorithms using this benchmark suite, and report the results by submitting a paper to the associated niching special session (i.e., submitting via the online submission system of CEC'2015). In case it is too late to submit the paper (i.e., passing the CEC'2015 submission deadline), author may submit their results in a report directly to the special session organizers, in order to be considered for the competition.
