Modeling Relational Data with Graph Convolutional Networks

by   Michael Schlichtkrull, et al.

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


page 1

page 2

page 3

page 4


Composition-based Multi-Relational Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have recently been shown to be quite...

LinkNBed: Multi-Graph Representation Learning with Entity Linkage

Knowledge graphs have emerged as an important model for studying complex...

Link Prediction on N-ary Relational Data Based on Relatedness Evaluation

With the overwhelming popularity of Knowledge Graphs (KGs), researchers ...

TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction

Link prediction is an important and frequently studied task that contrib...

Relational Graph Attention Networks

We investigate Relational Graph Attention Networks, a class of models th...

Tensor Decompositions for temporal knowledge base completion

Most algorithms for representation learning and link prediction in relat...

Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs

In this work, we provide a new formulation for Graph Convolutional Neura...