A Comprehensive Survey of Knowledge Graph Reasoning: Approaches and Applications

Abstract

Knowledge graph reasoning (KGR) aims to infer novel knowledge based on existing facts in knowledge graphs (KGs), playing a crucial role in various cognition intelligence systems across diverse domains. The previous review works explore KGR models from specific perspectives such as KG types and embedding spaces. In contrast, this survey provides a more comprehensive perspective of KGR from foundational approaches and their applications. Notably, some seldom-attended approaches such as negative sampling strategies, popular open-source libraries, and rule-guided KGR paradigms are carefully reviewed. Besides, we explore advanced techniques, such as large language models (LLMs) and their impact on KGR. The comparison among foundational models are analyzed to declare their strengths and limitations. More interestingly, this is the first effort to provide a taxonomy of real-world KGR applications for both horizontal and vertical domains. Furthermore, we highlight the challenges and opportunities in the field of KGR, including trustworthiness, multimodal reasoning, continual learning, uncertainty and LLM-driven approaches. This work aims to bridge the gap between theoretical advancements and practical deployment of KGR models, and outline promising future directions.