An approach to calculate conceptual distance across multi-granularity based on three-way partial order structure

The computation of concept distances aids in understanding the interrelations among entities within knowledge graphs and uncovering implicit information. The existing studies predominantly focus on the conceptual distance of specific hierarchical levels without offering a unified framework for comprehensive exploration. To overcome the limitations of unidimensional approaches, this paper proposes a method for calculating concept distances at multiple granularities based on a three-way partial order structure. Specifically: (1) this study introduces a methodology for calculating inter-object similarity based on the three-way attribute partial order structure (APOS); (2) It proposes the application of the similarity matrix to delineate the structure of categories; (3) Based on the similarity matrix describing the three-way APOS of categories, we establish a novel method for calculating inter-category distance. The experiments on eight datasets demonstrate that this approach effectively differentiates various concepts and computes their distances. When applied to classification tasks, it exhibits outstanding performance.