One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion

TL;DR

This paper introduces a novel global-local anchor representation method for inductive knowledge graph completion, enabling efficient reasoning on shared opening subgraphs and improving performance on unseen entities.

Contribution

It proposes extracting a shared opening subgraph for all candidates and designing transferable global and local anchors for entity-independent feature learning.

Findings

Outperforms most state-of-the-art methods in inductive KGC

Reduces reasoning time by avoiding repeated subgraph extraction

Effectively learns features for unseen entities

Abstract

Knowledge Graph Completion (KGC) has garnered massive research interest recently, and most existing methods are designed following a transductive setting where all entities are observed during training. Despite the great progress on the transductive KGC, these methods struggle to conduct reasoning on emerging KGs involving unseen entities. Thus, inductive KGC, which aims to deduce missing links among unseen entities, has become a new trend. Many existing studies transform inductive KGC as a graph classification problem by extracting enclosing subgraphs surrounding each candidate triple. Unfortunately, they still face certain challenges, such as the expensive time consumption caused by the repeat extraction of enclosing subgraphs, and the deficiency of entity-independent feature learning. To address these issues, we propose a global-local anchor representation (GLAR) learning method for inductive KGC. Unlike previous methods that utilize enclosing subgraphs, we extract a shared opening subgraph for all candidates and perform reasoning on it, enabling the model to perform reasoning more efficiently. Moreover, we design some transferable global and local anchors to learn rich entity-independent features for emerging entities. Finally, a global-local graph reasoning model is applied on the opening subgraph to rank all candidates. Extensive experiments show that our GLAR outperforms most existing state-of-the-art methods.