RNNCTPs: A Neural Symbolic Reasoning Method Using Dynamic Knowledge Partitioning Technology

TL;DR

RNNCTPs is a neural symbolic reasoning approach that enhances knowledge graph link prediction efficiency through dynamic knowledge partitioning, combining interpretability with competitive accuracy.

Contribution

The paper introduces RNNCTPs, a novel neural symbolic reasoning method that improves computational efficiency and interpretability in knowledge graph link prediction.

Findings

Achieves competitive performance on four datasets.

Less sensitive to embedding size parameter.

Demonstrates higher applicability compared to traditional CTPs.

Abstract

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.