SRGCN: Graph-based multi-hop reasoning on knowledge graphs

Zikang Wang, Linjing Li, Daniel Zeng

Research output: Contribution to journalArticlepeer-review

Abstract

Learning to infer missing links is one of the fundamental tasks in the knowledge graph. Instead of reasoning based on separate paths in the existing methods, in this paper, we propose a new model, Sequential Relational Graph Convolutional Network (SRGCN), which treats the multiple paths between an entity pair as a sequence of subgraphs. Specifically, to reason the relationship between two entities, we first construct a graph for the entities based on the knowledge graph and serialize the graph to a sequence. For each hop in the sequence, Relational Graph Convolutional Network (R-GCN) is then applied to update the embeddings of the entities. The updated embedding of the tail entity contains information of the entire graph, hence the relationship between two entities can be inferred from it. Compared to the existing approaches that deal with paths separately, SRGCN treats the graph as a whole, which can encode structural information and interactions between paths better. Experiments show that SRGCN outperforms path-based baselines on both link and fact prediction tasks. We also show that SRGCN is highly efficient in the sense that only one epoch of training is enough to achieve high accuracy, and even partial datasets can lead to competitive performance.

Original languageEnglish (US)
Pages (from-to)280-290
Number of pages11
JournalNeurocomputing
Volume454
DOIs
StatePublished - Sep 24 2021

Keywords

  • Graph convolutional network
  • Knowledge graph
  • Multi-hop reasoning

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'SRGCN: Graph-based multi-hop reasoning on knowledge graphs'. Together they form a unique fingerprint.

Cite this