不依赖随机游走，直接拉近邻接节点嵌入向量。
Node Embeddings via Neighbor Embeddings
- 通过邻接节点嵌入直接对齐，避免随机游走
- 在保留局部结构上显著优于现有算法
- 可生成更优的二维图布局，适合可视化
节点嵌入是无参数图表示学习范式，将图节点映射到向量空间以支持下游任务。当前先进方法如 DeepWalk 和 node2vec 基于节点相似性的随机游走和对比学习。本文提出图邻接嵌入（graph NE）框架，直接拉近相邻节点的嵌入向量，无需任何随机游走。实验表明，graph NE 在保留局部结构方面显著优于现有节点嵌入算法。此外，将其应用于二维节点嵌入问题，得到的 graph t-SNE 布局也优于现有图布局算法。
原文摘要 · Abstract (English)
Node embeddings are a paradigm in non-parametric graph representation learning, where graph nodes are embedded into a given vector space to enable downstream processing. State-of-the-art node-embedding algorithms, such as DeepWalk and node2vec, are based on random-walk notions of node similarity and on contrastive learning. In this work, we introduce the graph neighbor-embedding (graph NE) framework that directly pulls together embedding vectors of adjacent nodes without relying on any random walks. We show that graph NE strongly outperforms state-of-the-art node-embedding algorithms in terms of local structure preservation. Furthermore, we apply graph NE to the 2D node-embedding problem, obtaining graph t-SNE layouts that also outperform existing graph-layout algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。