Graph layouts and node embeddings are two distinct paradigms for non-parametric graph representation learning. In the former, nodes are embedded into 2D space for visualization purposes. In the latter, nodes are embedded into a high-dimensional vector space for downstream processing. State-of-the-art algorithms for these two paradigms, force-directed layouts and random-walk-based contrastive learning (such as DeepWalk and node2vec), have little in common. In this work, we show that both paradigms can be approached with a single coherent framework based on established neighbor embedding methods. Specifically, we introduce graph t-SNE, a neighbor embedding method for two-dimensional graph layouts, and graph CNE, a contrastive neighbor embedding method that produces high-dimensional node representations by optimizing the InfoNCE objective. We show that both graph t-SNE and graph CNE strongly outperform state-of-the-art algorithms in terms of local structure preservation, while being conceptually simpler.
View on arXiv@article{böhm2025_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 }
}