Tip the Balance: Improving Exploration of Balanced Crossover Operators by Adaptive Bias
This addresses a specific issue in discrete optimization for researchers using Genetic Algorithms, but it is incremental as it builds on existing crossover methods.
The paper tackled the problem of balanced crossover operators in Genetic Algorithms making the fitness landscape harder to explore, and found that applying an adaptive bias strategy to introduce unbalancedness improved performance, increasing the number of optimal solutions found for the balanced nonlinear Boolean functions problem.
The use of balanced crossover operators in Genetic Algorithms (GA) ensures that the binary strings generated as offsprings have the same Hamming weight of the parents, a constraint which is sought in certain discrete optimization problems. Although this method reduces the size of the search space, the resulting fitness landscape often becomes more difficult for the GA to explore and to discover optimal solutions. This issue has been studied in this paper by applying an adaptive bias strategy to a counter-based crossover operator that introduces unbalancedness in the offspring with a certain probability, which is decreased throughout the evolutionary process. Experiments show that improving the exploration of the search space with this adaptive bias strategy is beneficial for the GA performances in terms of the number of optimal solutions found for the balanced nonlinear Boolean functions problem.