ProjE: Embedding Projection for Knowledge Graph Completion

TL;DR

ProjE is a simple yet effective neural network model that improves knowledge graph completion by learning joint embeddings and modifying the loss function, outperforming complex models with fewer parameters.

Contribution

The paper introduces ProjE, a neural network architecture with subtle modifications that surpasses state-of-the-art models in knowledge graph completion without complex feature engineering.

Findings

ProjE outperforms current best methods by 37% on standard datasets.

ProjE has a smaller parameter size than most existing models.

ProjE effectively assesses the truthfulness of declarative statements.

Abstract

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph's entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing $37\%$ better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.