ScholarGate
助手
Machine learningGraph representation

知识图谱嵌入

知识图谱嵌入(Knowledge Graph Embeddings, KGE)是一类方法,它将知识图谱中的实体和关系表示为连续空间中的密集低维向量。其基础模型TransE由Bordes、Usunier、García-Durán、Weston和Yakhnenko于2013年提出。TransE将每个关系视为嵌入空间中的一种“翻译”——对于任何真实的三元组(h, r, t),头实体向量加上关系向量应近似于尾实体向量。这种简单的几何原理使得大规模的链接预测和知识库补全成为可能。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

来源

  1. Bordes, A., Usunier, N., García-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems, 26. link

如何引用本页

ScholarGate. (2026, June 2). Knowledge Graph Embeddings (TransE and beyond). ScholarGate. https://scholargate.app/zh/network-analysis/knowledge-graph-embeddings

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

被引用于

ScholarGateKnowledge Graph Embeddings (Knowledge Graph Embeddings (TransE and beyond)). 于 2026-06-15 检索自 https://scholargate.app/zh/network-analysis/knowledge-graph-embeddings · 数据集: https://doi.org/10.5281/zenodo.20539026