MuLAN: Multi-level attention-enhanced matching network for few-shot knowledge graph completion.
Neural Netw
; 174: 106222, 2024 Jun.
Article
em En
| MEDLINE
| ID: mdl-38442490
ABSTRACT
Recent years have witnessed increasing interest in the few-shot knowledge graph completion due to its potential to augment the coverage of few-shot relations in knowledge graphs. Existing methods often use the one-hop neighbors of the entity to enhance its embedding and match the query instance and support set at the instance level. However, such methods cannot handle inter-neighbor interaction, local entity matching and the varying significance of feature dimensions. To bridge this gap, we propose the Multi-Level Attention-enhanced matching Network (MuLAN) for few-shot knowledge graph completion. In MuLAN, a multi-head self-attention neighbor encoder is designed to capture the inter-neighbor interaction and learn the entity embeddings. Then, entity-level attention and instance-level attention are responsible for matching the query instance and support set from the local and global perspectives, respectively, while feature-level attention is utilized to calculate the weights of the feature dimensions. Furthermore, we design a consistency constraint to ensure the support instance embeddings are close to each other. Extensive experiments based on two well-known datasets (i.e., NELL-One and Wiki-One) demonstrate significant advantages of MuLAN over 11 state-of-the-art competitors. Compared to the best-performing baseline, MuLAN achieves 14.5% higher MRR and 13.3% higher Hits@K on average.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Reconhecimento Automatizado de Padrão
/
Conhecimento
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article