A Network Analysis-Driven Framework for Factual Explainability of Knowledge Graphs

Knowledge Graphs are widely used to represent knowledge structures in complex domains. In most real-world scenarios, these knowledge structures are dynamic. As a result, measures must be developed to assess the robustness and usability of Knowledge Graphs in temporal settings. Additionally, the explainability of inherent knowledge constituents is crucial for the desired attention of Knowledge Graphs, particularly in temporal settings. In this paper, we developed a framework to understand the robustness of factual explainability of Knowledge Graphs. The method is further verified by using meso-level attributes of the knowledge graph. The complex network analysis along with the community structures are co-evaluated through homophilic and heterophilic properties within the graph to validate the robustness of the factual interpretations. The analysis reveals that symbolic representation could be used as a reasonable metric for extracting link-based communities.