Word2VecGD: Neural Graph Drawing with Cosine-Stress Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915506364088320 |
|---|---|
| author | Yang, Minglai Ahmed, Reyan |
| author_facet | Yang, Minglai Ahmed, Reyan |
| contents | We propose a novel graph visualization method leveraging random walk-based embeddings to replace costly graph-theoretical distance computations. Using word2vec-inspired embeddings, our approach captures both structural and semantic relationships efficiently. Instead of relying on exact shortest-path distances, we optimize layouts using cosine dissimilarities, significantly reducing computational overhead. Our framework integrates differentiable stress optimization with stochastic gradient descent (SGD), supporting multi-criteria layout objectives. Experimental results demonstrate that our method produces high-quality, semantically meaningful layouts while efficiently scaling to large graphs. Code available at: https://github.com/mlyann/graphv_nn |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17333 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Word2VecGD: Neural Graph Drawing with Cosine-Stress Optimization Yang, Minglai Ahmed, Reyan Computational Geometry Machine Learning We propose a novel graph visualization method leveraging random walk-based embeddings to replace costly graph-theoretical distance computations. Using word2vec-inspired embeddings, our approach captures both structural and semantic relationships efficiently. Instead of relying on exact shortest-path distances, we optimize layouts using cosine dissimilarities, significantly reducing computational overhead. Our framework integrates differentiable stress optimization with stochastic gradient descent (SGD), supporting multi-criteria layout objectives. Experimental results demonstrate that our method produces high-quality, semantically meaningful layouts while efficiently scaling to large graphs. Code available at: https://github.com/mlyann/graphv_nn |
| title | Word2VecGD: Neural Graph Drawing with Cosine-Stress Optimization |
| topic | Computational Geometry Machine Learning |
| url | https://arxiv.org/abs/2509.17333 |