On Multi-Relational Link Prediction with Bilinear Models
This work provides a systematic comparison and ensemble method for bilinear models in knowledge graph completion, which is incremental but useful for researchers in the field.
The paper analyzes bilinear embedding models for multi-relational link prediction and knowledge graph completion, exploring their expressiveness and connections, and shows that relation-level ensembles of these models achieve state-of-the-art performance.
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.