VERSE: Versatile Graph Embeddings From Similarity Measures

Abstract

Embedding a web-scale information network into a low-dimensional vector space facilitates tasks such as link prediction, classification, and visualization. Past research has addressed the problem of extracting such embeddings by adopting methods from words to graphs, without defining a clearly comprehensible graph-related objective. Yet, as we show, the objectives used in past works implicitly utilize similarity measures among graph nodes. In this paper, we carry the similarity orientation of previous works to its logical conclusion; we propose VERtex Similarity Embeddings (VERSE), a simple, versatile, and memory-efficient method that derives graph embeddings explicitly calibrated to preserve the distributions of a selected vertex-to-vertex similarity measure. VERSE learns such embeddings by training a single-layer neural network. While its default, scalable version does so via sampling similarity information, we also develop a variant using the full information per vertex. Our exper

Stats

• citations209
• S2 citations—
• github stars0
• HF likes0
• heat score17.42
• arxiv keytsitsulin2018verse

Related papers

• Hebbian Graph Embeddings (2019)0.00
• Meta-path Guided Embedding For Similarity Search In Large-scale Heterogeneous Information Networks (2016)0.00
• FREDE: Anytime Graph Embeddings (2020)11.39
• Vexir2vec: An Architecture-neutral Embedding Framework For Binary Similarity (2023)5.84
• Evaluating The Impact Of Word Embeddings On Similarity Scoring In Practical Information Retrieval (2026)0.00
• QUINT: Node Embedding Using Network Hashing (2021)5.24
• A Survey On Efficient Processing Of Similarity Queries Over Neural Embeddings (2022)0.00
• Scene Graph Embeddings Using Relative Similarity Supervision (2021)7.50