Neural Theorem Provers Delineating Search Area Using RNN
This work addresses efficiency issues in knowledge graph reasoning for AI applications, but it appears incremental as it builds on existing neural theorem proving methods.
The paper tackled the computational inefficiency of Neural Theorem Provers in knowledge graph link prediction by proposing an RNN-based method with a generalized EM approach, resulting in competitive performance across four datasets.
Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graphs link prediction has been limited due to their computational inefficiency. A new RNNNTP method is proposed in this paper, using a generalized EM-based approach to continuously improve the computational efficiency of Neural Theorem Provers(NTPs). The RNNNTP is divided into relation generator and predictor. The relation generator is trained effectively and interpretably, so that the whole model can be carried out according to the development of the training, and the computational efficiency is also greatly improved. In all four data-sets, this method shows competitive performance on the link prediction task relative to traditional methods as well as one of the current strong competitive methods.