Modeling Relational Data with Graph Convolutional Networks

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification AIFB R-GCN Accuracy 95.83 # 1
Node Classification AM R-GCN Accuracy 89.29 # 3
Node Classification BGS R-GCN Accuracy 83.10 # 5
Node Classification MUTAG R-GCN Accuracy 73.23 # 4
Node Property Prediction ogbn-mag Full-batch R-GCN Test Accuracy 0.3977 ± 0.0046 # 32
Validation Accuracy 0.4084 ± 0.0041 # 31
Number of params 154366772 # 4
Ext. data No # 1
Node Property Prediction ogbn-mag R-GSN Test Accuracy 0.5032 ± 0.0037 # 24
Validation Accuracy 0.5182 ± 0.0041 # 24
Number of params 154373028 # 3
Ext. data No # 1