A Retrieve-and-Read Framework for Knowledge Graph Link Prediction

TL;DR

This paper introduces a retrieve-and-read framework for knowledge graph link prediction that improves efficiency and accuracy by focusing on relevant subgraphs and employing a Transformer-based GNN reader.

Contribution

It proposes a novel framework that retrieves relevant subgraphs and uses a Transformer-based GNN for joint reasoning, addressing limitations of traditional GNNs.

Findings

Competitive performance on standard datasets

Effective focus on salient context information

Insights for designing better retrievers

Abstract

Knowledge graph (KG) link prediction aims to infer new facts based on existing facts in the KG. Recent studies have shown that using the graph neighborhood of a node via graph neural networks (GNNs) provides more useful information compared to just using the query information. Conventional GNNs for KG link prediction follow the standard message-passing paradigm on the entire KG, which leads to superfluous computation, over-smoothing of node representations, and also limits their expressive power. On a large scale, it becomes computationally expensive to aggregate useful information from the entire KG for inference. To address the limitations of existing KG link prediction frameworks, we propose a novel retrieve-and-read framework, which first retrieves a relevant subgraph context for the query and then jointly reasons over the context and the query with a high-capacity reader. As part of our exemplar instantiation for the new framework, we propose a novel Transformer-based GNN as the reader, which incorporates graph-based attention structure and cross-attention between query and context for deep fusion. This simple yet effective design enables the model to focus on salient context information relevant to the query. Empirical results on two standard KG link prediction datasets demonstrate the competitive performance of the proposed method. Furthermore, our analysis yields valuable insights for designing improved retrievers within the framework.