RNNCTPs: A Neural Symbolic Reasoning Method Using Dynamic Knowledge Partitioning Technology
This work addresses computational bottlenecks in knowledge graph reasoning for AI researchers, but it is incremental as it builds on existing Conditional Theorem Provers.
The paper tackles the low computational efficiency of symbolic reasoning in knowledge graph link prediction by proposing RNNCTPs, a neural symbolic method that uses dynamic knowledge partitioning to improve efficiency and reduce sensitivity to embedding size, achieving competitive performance on four datasets.
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.