A label-free similarity measure between workflow nets

Many activities in business process management, such as process search, process clustering, and process mining, need to determine the similarity between two process models. Although several approaches have recently been proposed to measure the behavioral similarity between business processes, all of them require that tasks in processes are properly labeled. According to these approaches, similarity between two given processes can be dramatically different under different task labeling schemes. In this paper, we consider process similarity measure from another view point, i.e., focusing on the control flow structures and ignoring the task labels. Thus, we propose a label-free similarity measure between process models based on transition adjacent relations (TARs) in the context of workflow nets (WF-nets), as well as an efficient algorithm. The experimental results involving comparison of different similarity measures on artificial processes and evaluation of the efficient algorithm on real-life processes are discussed.