2022/04/19 by Yu-hao Wu, Wu, Yu-hao, Hou‐Biao Li +2
Computer Science · Materials Science · Mathematics · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #F.4.1 #FOS: Computer and information sciences #FOS: Mathematics #Graph Theory and Algorithms #Logic (math.LO) #Machine Learning in Materials Science #Numerical Analysis (math.NA) #cs.AI #cs.NA #math.LO #math.NA #msc:F.4.1
paper · pdf · doi:10.48550/arxiv.2204.08810
16 pages, 8 figures,5 tables
arxiv created 2022/04/19 · openalex publication_date 2022/04/19 · arxiv updated 2022/04/20 · openalex created_date 2022/04/27 · openalex updated_date 2026/07/28
Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graph link prediction is limited due to their low computational efficiency. In this paper, we propose a new neural symbolic reasoning method: RNNCTPs, which improves computational efficiency by re-filtering the knowledge selection of Conditional Theorem Provers (CTPs), and is less sensitive to the embedding size parameter. RNNCTPs are divided into relation selectors and predictors. The relation selectors are trained efficiently and interpretably, so that the whole model can dynamically generate knowledge for the inference of the predictor. In all four datasets, the method shows competitive performance against traditional methods on the link prediction task, and can have higher applicability to the selection of datasets relative to CTPs.