Expanding the Scope: Inductive Knowledge Graph Reasoning with Multi-Starting Progressive Propagation

TL;DR

This paper introduces MStar, a novel inductive knowledge graph reasoning model that uses multiple starting points and a highway layer to improve message propagation, achieving better results on distant entities.

Contribution

MStar leverages conditional message passing with multiple query-specific starting entities and a highway layer, advancing inductive KG reasoning capabilities.

Findings

MStar outperforms state-of-the-art models on distant entity reasoning.

The highway layer enhances message propagation efficiency.

LinkVerify training reduces noise impact.

Abstract

Knowledge graphs (KGs) are widely acknowledged as incomplete, and new entities are constantly emerging in the real world. Inductive KG reasoning aims to predict missing facts for these new entities. Among existing models, graph neural networks (GNNs) based ones have shown promising performance for this task. However, they are still challenged by inefficient message propagation due to the distance and scalability issues. In this paper, we propose a new inductive KG reasoning model, MStar, by leveraging conditional message passing neural networks (C-MPNNs). Our key insight is to select multiple query-specific starting entities to expand the scope of progressive propagation. To propagate query-related messages to a farther area within limited steps, we subsequently design a highway layer to propagate information toward these selected starting entities. Moreover, we introduce a training strategy called LinkVerify to mitigate the impact of noisy training samples. Experimental results validate that MStar achieves superior performance compared with state-of-the-art models, especially for distant entities.