Modeling Relational Data with Graph Convolutional Networks

TL;DR

This paper introduces Relational Graph Convolutional Networks (R-GCNs) for knowledge graph completion, demonstrating their effectiveness in entity classification and enhancing link prediction models with significant performance improvements.

Contribution

The paper presents R-GCNs tailored for multi-relational data, improving knowledge base completion tasks and integrating them with existing models for better inference.

Findings

R-GCNs outperform baseline models in entity classification.

Enriching factorization models with R-GCNs improves link prediction accuracy.

Achieved a 29.8% improvement on FB15k-237 dataset.

Abstract

Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and apply them to two standard knowledge base completion tasks: Link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes). R-GCNs are related to a recent class of neural networks operating on graphs, and are developed specifically to deal with the highly multi-relational data characteristic of realistic knowledge bases. We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification. We further show that factorization models for link prediction such as DistMult can be significantly improved by enriching them with an encoder model to accumulate evidence over multiple inference steps in the relational graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.