Process / pipeline
网络嵌入 — Node2Vec、DeepWalk、LINE
网络嵌入是一类表征学习方法，它将图的每个节点映射到密集、低维的向量中，同时保留网络的结构属性。Perozzi、Al-Rfou 和 Skiena 在 DeepWalk (2014) 中首次将该方法形式化应用于社交网络数据，该方法将 Word2Vec 的 skip-gram 模型应用于图上的随机游走。Grover 和 Leskovec 在 Node2Vec (2016) 中对其进行了扩展，引入了一种有偏随机游走，平衡了广度优先和深度优先探索。这些嵌入将关系数据转换为特征向量，可供标准机器学习分类器和聚类算法直接使用。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Grover, A. & Leskovec, J. (2016). Node2Vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 855-864. DOI: 10.1145/2939672.2939754 ↗
- Perozzi, B., Al-Rfou, R., & Skiena, S. (2014). DeepWalk: Online Learning of Social Representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 701-710. DOI: 10.1145/2623330.2623732 ↗
如何引用本页
ScholarGate. (2026, June 1). Network Embedding (Node2Vec, DeepWalk, LINE). ScholarGate. https://scholargate.app/zh/network-analysis/network-embedding
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 →