Knowledge Graph Reasoning with Relational Digraph

TL;DR

This paper introduces RED-GNN, a novel graph neural network that efficiently encodes relational directed graphs to improve reasoning on knowledge graphs, providing interpretable evidence and significant performance gains.

Contribution

The paper proposes RED-GNN, a new GNN variant that captures local evidence in knowledge graphs using relational directed graphs with query-dependent attention mechanisms.

Findings

RED-GNN achieves superior performance in reasoning tasks.

The model provides interpretable evidence through attention weights.

RED-GNN is efficient for both inductive and transductive reasoning.

Abstract

Reasoning on the knowledge graph (KG) aims to infer new facts from existing ones. Methods based on the relational path have shown strong, interpretable, and transferable reasoning ability. However, paths are naturally limited in capturing local evidence in graphs. In this paper, we introduce a novel relational structure, i.e., relational directed graph (r-digraph), which is composed of overlapped relational paths, to capture the KG's local evidence. Since the r- digraphs are more complex than paths, how to efficiently construct and effectively learn from them are challenging. Directly encoding the r-digraphs cannot scale well and capturing query-dependent information is hard in r-digraphs. We propose a variant of graph neural network, i.e., RED-GNN, to address the above challenges. Specifically, RED-GNN makes use of dynamic programming to recursively encodes multiple r-digraphs with shared edges, and utilizes a query-dependent attention mechanism to select the strongly correlated edges. We demonstrate that RED-GNN is not only efficient but also can achieve significant performance gains in both inductive and transductive reasoning tasks over existing methods. Besides, the learned attention weights in RED-GNN can exhibit interpretable evidence for KG reasoning.