MDDE: multitasking distributed differential evolution for privacy-preserving database fragmentation

Database fragmentation has been used as a protection mechanism of database's privacy by allocating attributes with sensitive associations into separate data fragments. A typical relational database consists of multiple relations. Thus, fragmentation process is applied to each relation separately in a sequential manner. In other words, the existing database fragmentation approaches regard each relation fragmentation problem as an independent task. When solving a sequence of fragmentation problems, redundant computational resources are consumed when extracting the same fragmentation information and limit the performance of those algorithms. In this paper, a multitasking database fragmentation problem for privacy preservation requirements is formally defined. A multitasking distributed differential evolution algorithm is introduced, including a multitasking distributed framework enriched by two new operators. The introduced framework can help exchange generic and effective allocation information among different database fragmentation problems. A similarity-based alignment operator is proposed to adjust the fragment orders in different database fragmentation solutions. A perturbation-based mutation operator with adaptive mutation strategy selection is designed to sufficiently exchange evolutionary information in the solutions. Experimental results show that the proposed algorithm can outperform other competitors in terms of solution accuracy, convergence speed, and scalability.