基于大语言模型与适配器驱动的知识图谱补全算法OA

Aiming at the problems that the knowledge graph completion method based on Transformer as the backbone network,included parameter redundancy in feed-forward networks,difficulties in identifying tail entities under commonsense scenarios,and embedding biases in contrastive learning,we proposed an adapter-enhanced knowledge graph completion algorithm that integrated large language models with multi-positive sample contrastive learning.The algorithm reduced redundant features by introducing multi-head adapters in feed-forward network,and utilized large language models to enhance commonsense reasoning ability.At the same time,it corrected embedding biases through multi-positive sample contrastive learning.Experimental results show that,compared to the current state-of-the-art models,the algorithm improves MRR by 5.4％and 9.2％on WN18RR and FB15k-237 datasets,respectively,and by 3.6％and 6.7％in transductive and inductive settings on the more complex Wikidata5M dataset,respectively,and demonstrates superior generalization ability under low-resource and complex scenarios.