Message Intercommunication for Inductive Relation Reasoning

TL;DR

This paper introduces MINES, a novel GraIL-based model for inductive relation reasoning in knowledge graphs, which enhances information sharing between entities and extends neighborhood scope to improve reasoning capabilities.

Contribution

The paper proposes a Message Intercommunication mechanism and neighbor-enhanced subgraph extraction to address limitations of existing models, significantly improving reasoning performance.

Findings

MINES outperforms state-of-the-art models on twelve datasets.

The intercommunication mechanism effectively captures hidden mutual relations.

Extending neighborhood scope enhances information collection for reasoning.

Abstract

Inductive relation reasoning for knowledge graphs, aiming to infer missing links between brand-new entities, has drawn increasing attention. The models developed based on Graph Inductive Learning, called GraIL-based models, have shown promising potential for this task. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based inductive relation reasoning model, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments on twelve inductive benchmark datasets demonstrate that our MINES outperforms existing state-of-the-art models, and show the effectiveness of our intercommunication mechanism and reasoning on the neighbor-enhanced subgraph.