Comprehensible Artificial Intelligence on Knowledge Graphs: A survey
Simon Schramm, Christoph Wehner, Ute Schmid
TL;DR
This survey addresses the need for comprehensible AI in knowledge-graph–based systems by clarifying the distinction between Interpretable Machine Learning (IML) and Explainable AI (XAI) within a unifying Comprehensible Artificial Intelligence (CAI) framework for KGs. It introduces a detailed taxonomy across representations, tasks, and foundational approaches, and summarizes 55 key works (out of 163) that span rule mining, pathfinding, embeddings, and graph-generation/explanation techniques. The authors highlight KG-specific considerations, such as semantic richness and cyclic structures, and identify gaps like scarce XAI methods for link prediction, the need for standardized KG-centric evaluation, and the potential of integrating non-graph modalities. By organizing the literature into IML and XAI lines and mapping them to a unified CAI taxonomy, the work provides a structured roadmap for advancing trustworthy, human-centered AI on knowledge graphs. The practical impact lies in guiding researchers and practitioners toward methods that produce faithful, interpretable explanations tailored to KG data, ultimately enabling safer deployment of KG-based AI in high-stakes domains.
Abstract
Artificial Intelligence applications gradually move outside the safe walls of research labs and invade our daily lives. This is also true for Machine Learning methods on Knowledge Graphs, which has led to a steady increase in their application since the beginning of the 21st century. However, in many applications, users require an explanation of the Artificial Intelligences decision. This led to increased demand for Comprehensible Artificial Intelligence. Knowledge Graphs epitomize fertile soil for Comprehensible Artificial Intelligence, due to their ability to display connected data, i.e. knowledge, in a human- as well as machine-readable way. This survey gives a short history to Comprehensible Artificial Intelligence on Knowledge Graphs. Furthermore, we contribute by arguing that the concept Explainable Artificial Intelligence is overloaded and overlapping with Interpretable Machine Learning. By introducing the parent concept Comprehensible Artificial Intelligence, we provide a clear-cut distinction of both concepts while accounting for their similarities. Thus, we provide in this survey a case for Comprehensible Artificial Intelligence on Knowledge Graphs consisting of Interpretable Machine Learning on Knowledge Graphs and Explainable Artificial Intelligence on Knowledge Graphs. This leads to the introduction of a novel taxonomy for Comprehensible Artificial Intelligence on Knowledge Graphs. In addition, a comprehensive overview of the research on Comprehensible Artificial Intelligence on Knowledge Graphs is presented and put into the context of the taxonomy. Finally, research gaps in the field of Comprehensible Artificial Intelligence on Knowledge Graphs are identified for future research.