.png){kind=icon}
返回
Knowledge embedding via hyperbolic skipped graph convolutional networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.01.037.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the aim of constructing a low-dimensional representation space, Hyperbolic Knowledge Embeddings have gradually become a hot spot in various information retrieval and machine learning tasks. However, most of the existing Hyperbolic knowledge embedding methods focus on the shallow embedding, and often ignore the network structure characteristics (e.g., hierarchy) of Knowledge Graphs. Therefore, this paper designs a novel Hyperbolic Skipped Knowledge Graph Convolutional Network, HSKGCN, to improve link prediction accuracy with low embedding dimension requirements. Firstly, the model is designed based on the hyperbolic geometric operations on the Poincare ball, which can effectively utilize the characteristics of the hyperbolic geometry (e.g., Poincare ball) to capture the hierarchy of Knowledge Graphs; Secondly, each single-layer convolutional layer introduces the feature aggregation weight, which ensures the reasonable distribution of node features during the aggregation process; In addition, the skip-connection mechanism is applied to HSKGCN to weaken the information loss caused by the stacked of the graph convolutional layers; Finally, we evaluate HSKGCN on benchmark datasets, WN18RR and FB15k-237. Experiments show that HSKGCN achieves substantial improvements against state-of-the-art models on the 32-dimensional embedding task, and the results of different relations on WN18RR show graphs similar with tree topology can performer better. (c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Hyperbolic space
Poincare ball
Knowledge graphs
Knowledge embedding
Knowledge representation
Link prediction
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
分享收藏A knowledge graph method for hazardous chemical management: Ontology design and entity identification.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Knowledge Graph Embedding via Graph Attenuated Attention Networks基于图衰减注意力网络的知识图谱嵌入IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Heterogeneous graph reasoning for knowledge-grounded medical dialogue system基于知识的医学对话系统的异构图推理NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏SRGCN: Graph-based multi-hop reasoning on knowledge graphsSRGCN: 基于图的知识图多跳推理NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
没有更多内容
没有更多内容