Semantic Similarity of Workflow Traces with Various Granularities

Qing Liu, Yi Yang, Quan Bai

Abstract: A workflow trace describes provenance information of a particular workflow execution. Understanding workflow traces and their similarity have many applications in both scientific research and business world. Given workflow traces generated by heterogeneous systems with difference granularities, it is a challenge for users to understand their similarities. In this work, we investigate workflow traces’ granularity problem and their similarity method. Algorithms are developed to transform a trace into its multi-granularity forms assisting by a workflow trace ontology. A novel generic semantic similarity algorithm is proposed that not only considers the structural similarity but also the semantics coverage embedded in traces during transformation. Furthermore, theoretical analysis is presented to compute the maximum semantic similarity. Our approach enables that two workflow traces can be compared with any granularity. The experiment using real world workflow traces demonstrates the effectiveness of the proposed methods.