KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

TL;DR

KBLRN is a novel end-to-end framework that combines latent, relational, and numerical features for knowledge base representation learning, outperforming existing methods on completion tasks.

Contribution

It introduces a new integrated approach combining neural and probabilistic models for knowledge base learning, including novel datasets with numerical features.

Findings

KBLRN outperforms existing methods on knowledge base completion tasks.

Numerical features significantly impact KB completion performance.

New datasets with numerical features are provided for benchmarking.

Abstract

We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. KBLRN integrates feature types with a novel combination of neural representation learning and probabilistic product of experts models. To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. We contribute a novel data sets enriching commonly used knowledge base completion benchmarks with numerical features. The data sets are available under a permissive BSD-3 license. We also investigate the impact numerical features have on the KB completion performance of KBLRN.