Node Embeddings via Neighbor Embeddings

Jan Niklas Böhm, Marius Keute, Alica Guzmán, Sebastian Damrich, Andrew Draganov, Dmitry Kobak

Authors that are also TMLR Expert Reviewers: ~Dmitry_Kobak2

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.

Certifications: Expert Certification

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: Camera-ready version.

Code: https://github.com/berenslab/graph-ne-paper

Assigned Action Editor: ~Vicenç_Gómez1

Submission Number: 5674