A Modular Reasoning Approach to Knowledge Graph
Changlong Wang, Siyun Bi, Rong Zhang, Qibin Fu, Tingting Gan · 2022
The construction and application of Knowledge Graph require effective reasoning support. However, the standard reasoning engines can not effectively deal with large-scale Knowledge Graphs because they load and compute Knowledge Graphs as a whole. This paper proposes a modular reasoning approach to Knowledge Graph. Firstly, the facts in the Knowledge Graph are partitioned into modules according to the predicate type and entity. Then the concepts and attributes involved in the fact module are used as seed signatures to extract the ontology module from the schema. During the reasoning procedure, the reasoning engine partially loads fact modules and the related ontology modules. Experiments show that the proposed approach can deal with large-scale Knowledge Graphs in a modular way with less time and memory.