.png){kind=icon}
返回
Low-resource knowledge graph completion based on knowledge distillation driven by large language models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.112622.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Knowledge graph completion (KGC) refines the existing knowledge graph (KG) by predicting missing entities or relations. Existing methods are mainly based on embeddings or texts but only perform better with abundant labeled data. Hence, KGC in resource-constrained settings is a significant problem, which faces challenges of data imbalance across relations and lack of relation label semantics. Considering that Large Language Models (LLMs) demonstrate powerful reasoning and generation capabilities, this work proposes an LLM-driven Knowledge Graph Completion Distillation (KGCD) model to address low-resource KGC. A two-stage framework is developed, involving teacher-student distillation by using LLM to improve reasoning, followed by fine-tuning on real-world low-resource datasets. To deal with data imbalance, a hybrid prompt design for LLM is proposed, which includes rethink and open prompts. Furthermore, a virtual relation label generation strategy enhances the model's understanding of triples. Extensive experiments on three benchmarks have shown that KGCD's effectiveness for low-resource KGC, achieving improvements in Mean Reciprocal Rank (MRR) by 11% and Hits@1 by 10% on the WN18, MRR by 10% and Hits@1 by 14% on the WN18RR, and MRR by 12% and Hits@1 by 11% on the YAGO3-10.
Keyword:
Knowledge graph completion
Knowledge reasoning
Link prediction
Large language models
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Matrix Effects in the Detection of Pb and Ba in Soils Using Laser-Induced Breakdown Spectroscopy使用激光诱导击穿光谱检测土壤中Pb和Ba的基质效应
PREAI
分享收藏Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion具有多方面信息的胶囊神经张量网络用于少镜头知识图补全.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Hippopotamus optimization algorithm: a novel nature-inspired optimization algorithmSCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏JointE: Jointly utilizing 1D and 2D convolution for knowledge graph embeddingJointE: 联合利用1D和2D卷积进行知识图谱嵌入
PREAI
分享收藏Dynamic prompt-based virtual assistant framework for BIM information search基于动态提示的BIM信息搜索虚拟助手框架
PREAI
分享收藏Heterogeneous relational reasoning in knowledge graphs with reinforcement learningINFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏分享收藏
查看更多内容