Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations

TL;DR

This paper introduces Meta-KGR, a meta-learning approach that enhances multi-hop reasoning over knowledge graphs, especially for few-shot relations, by quickly adapting from high-frequency relations, leading to improved performance.

Contribution

The paper proposes a novel meta-learning based method for multi-hop KG reasoning that effectively handles few-shot relations, outperforming existing methods.

Findings

Meta-KGR outperforms state-of-the-art methods on two datasets.

Meta-KGR effectively adapts from high-frequency to few-shot relations.

Experimental results demonstrate significant improvements in few-shot reasoning scenarios.

Abstract

Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task. Most previous methods assume that every relation in KGs has enough training triples, regardless of those few-shot relations which cannot provide sufficient triples for training robust reasoning models. In fact, the performance of existing multi-hop reasoning methods drops significantly on few-shot relations. In this paper, we propose a meta-based multi-hop reasoning method (Meta-KGR), which adopts meta-learning to learn effective meta parameters from high-frequency relations that could quickly adapt to few-shot relations. We evaluate Meta-KGR on two public datasets sampled from Freebase and NELL, and the experimental results show that Meta-KGR outperforms the current state-of-the-art methods in few-shot scenarios. Our code and datasets can be obtained from https://github.com/ THU-KEG/MetaKGR.