.png){kind=icon}
返回
Relphormer: Relational Graph Transformer for Knowledge Graph Representations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.127044.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge Graph (KG) representations, where the translational distance paradigm dominates this area. Note that vanilla Transformer architectures struggle to capture the intrinsically heterogeneous structural and semantic information of knowledge graphs. To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer. Specifically, we introduce Triple2Seq which can dynamically sample contextualized sub-graph sequences as the input to alleviate the heterogeneity issue. We propose a novel structure-enhanced self-attention mechanism to encode the relational information and keep the semantic information within entities and relations. Moreover, we utilize masked knowledge modeling for general knowledge graph representation learning, which can be applied to various KG-based tasks including knowledge graph completion, question answering, and recommendation. Experimental results on six datasets show that Relphormer can obtain better performance compared with baselines.2
Keyword:
Knowledge graph
Knowledge graph representation
Transformer
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
分享收藏The Unified Medical Language System (UMLS): integrating biomedical terminology统一医学语言系统 (UMLS): 整合生物医学术语.png)
NUCLEIC ACIDS RESEARCH
OAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏 没有更多内容
没有更多内容