Node Embeddings via Neighbor Embeddings
Abstract
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.
Cite
@article{arxiv.2503.23822,
title = {Node Embeddings via Neighbor Embeddings},
author = {Jan Niklas Böhm and Marius Keute and Alica Guzmán and Sebastian Damrich and Andrew Draganov and Dmitry Kobak},
journal= {arXiv preprint arXiv:2503.23822},
year = {2025}
}
Comments
Accepted to Transactions of Machine Learning Research (TMLR)