Node Embeddings via Neighbor Embeddings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909918437572608 |
|---|---|
| author | Böhm, Jan Niklas Keute, Marius Guzmán, Alica Damrich, Sebastian Draganov, Andrew Kobak, Dmitry |
| author_facet | Böhm, Jan Niklas Keute, Marius Guzmán, Alica Damrich, Sebastian Draganov, Andrew Kobak, Dmitry |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Node Embeddings via Neighbor Embeddings Böhm, Jan Niklas Keute, Marius Guzmán, Alica Damrich, Sebastian Draganov, Andrew Kobak, Dmitry Machine Learning 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. |
| title | Node Embeddings via Neighbor Embeddings |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.23822 |