Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
It addresses the problem of improving reasoning for applications such as information extraction and recommendation by combining robust neural methods with interpretable symbolic techniques, but it is incremental as a survey.
This survey examines the development of symbolic, neural, and hybrid reasoning methods on knowledge graphs, focusing on tasks like knowledge graph completion and question answering, and presents them within a unified framework.
Knowledge graph reasoning is the fundamental component to support machine learning applications such as information extraction, information retrieval, and recommendation. Since knowledge graphs can be viewed as the discrete symbolic representations of knowledge, reasoning on knowledge graphs can naturally leverage the symbolic techniques. However, symbolic reasoning is intolerant of the ambiguous and noisy data. On the contrary, the recent advances of deep learning promote neural reasoning on knowledge graphs, which is robust to the ambiguous and noisy data, but lacks interpretability compared to symbolic reasoning. Considering the advantages and disadvantages of both methodologies, recent efforts have been made on combining the two reasoning methods. In this survey, we take a thorough look at the development of the symbolic, neural and hybrid reasoning on knowledge graphs. We survey two specific reasoning tasks, knowledge graph completion and question answering on knowledge graphs, and explain them in a unified reasoning framework. We also briefly discuss the future directions for knowledge graph reasoning.