Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

TL;DR

This paper introduces a novel global-local framework with a gated and attentive neighbor aggregator and a meta-learning based TransH model to improve few-shot knowledge graph completion, effectively handling noisy neighbors and complex relations.

Contribution

The paper proposes a new global-local framework with a gated and attentive neighbor aggregator and a meta-learning based TransH for improved FKGC performance.

Findings

Outperforms state-of-the-art FKGC models on NELL-One and Wiki-One datasets.

Achieves 8.0% and 2.8% improvements in Hits@10 over MetaR.

Effectively filters noise neighbors and models complex relations in few-shot scenarios.

Abstract

Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to enhance its semantic representation. However, noise neighbor information might be amplified when the neighborhood is excessively sparse and no neighbor is available to represent the few-shot relation. Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances. Thus, inferring complex relations in the few-shot scenario is difficult for FKGC models due to limited training instances. In this paper, we propose a few-shot relational learning with global-local framework to address the above issues. At the global stage, a novel gated and attentive neighbor aggregator is built for accurately integrating the semantics of a few-shot relation's neighborhood, which helps filtering the noise neighbors even if a KG contains extremely sparse neighborhoods. For the local stage, a meta-learning based TransH (MTransH) method is designed to model complex relations and train our model in a few-shot learning fashion. Extensive experiments show that our model outperforms the state-of-the-art FKGC approaches on the frequently-used benchmark datasets NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on Wiki-One by the metric Hits@10.