On Multi-Relational Link Prediction with Bilinear Models

TL;DR

This paper investigates the expressiveness and relationships of bilinear models for multi-relational link prediction, demonstrating that relation-level ensembles can achieve state-of-the-art results in knowledge graph completion.

Contribution

It analyzes the expressiveness of various bilinear models, explores their constraints and subsumption relationships, and shows that ensembles of these models can improve prediction performance.

Findings

Bilinear models can be represented with specific constraints.

Certain bilinear models are universal in representing relations.

Ensembles of bilinear models achieve state-of-the-art performance.

Abstract

We study bilinear embedding models for the task of multi-relational link prediction and knowledge graph completion. Bilinear models belong to the most basic models for this task, they are comparably efficient to train and use, and they can provide good prediction performance. The main goal of this paper is to explore the expressiveness of and the connections between various bilinear models proposed in the literature. In particular, a substantial number of models can be represented as bilinear models with certain additional constraints enforced on the embeddings. We explore whether or not these constraints lead to universal models, which can in principle represent every set of relations, and whether or not there are subsumption relationships between various models. We report results of an independent experimental study that evaluates recent bilinear models in a common experimental setup. Finally, we provide evidence that relation-level ensembles of multiple bilinear models can achieve state-of-the art prediction performance.