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

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.

References in corpus (3)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Dynamically Fused Graph Network for Multi-hop Reasoning

Cited by in corpus (8)

• FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
• Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
• Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network
• Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
• Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion