.png){kind=icon}
返回
Heterogeneous graph structure learning for link prediction in knowledge hypergraphs
.png){kind=icon}
PRE
AI
DOI：10.1007/s13042-025-02827-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Knowledge hypergraphs, extending knowledge graphs, inherently exhibit heterogeneity from diverse entity types, relationships, and higher-order associations. Leveraging this enables nuanced representation of complex semantics and structures. However, existing knowledge hypergraph link prediction methods face critical challenges: inadequate modeling of high-order semantic relations results in (1) suboptimal utilization of hypergraph structural information, and (2) limited reasoning capabilities. Consequently, these methods fail to improve prediction performance. To address this, we introduce a novel heterogeneous graph structure learning framework. Specifically, the hypergraph is transformed into a heterogeneous graph with five node types and twelve edge types to fully exploit structural information. We further propose a hypergraph attention layer to capture structural features of nodes and edges, and a Transformer layer to model these features for predicting missing entities and relationships. Experiments on public datasets show that our method significantly outperforms baseline methods, confirming its effectiveness and robustness.
Keyword:
Heterogeneous graph structure
Hyper-relational representation
Link prediction
Transformer
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
.png){kind=icon}
分享收藏
Relation-attention semantic-correlative knowledge graph embedding for inductive link prediction
PREAI
分享收藏
查看更多内容