Learning Predictive Categories Using Lifted Relational Neural Networks

Gustav Sourek, Suresh Manandhar, Filip Zelezný, Steven Schockaert, Ondrej Kuzelka

Abstract: Lifted relational neural networks (LRNNs) are a flexible neural-symbolic framework based on the idea of lifted modelling. In this paper we show how LRNNs can be easily used to specify declaratively and solve learning problems in which latent categories of entities, properties and relations need to be jointly induced.