# Embedding Node Structural Role Identity into Hyperbolic Space

arXiv: https://arxiv.org/abs/2011.01512 · HTML: https://mlsanity.com/paper/2011.01512/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization](https://mlsanity.com/paper/2109.07016/) (2021)
- [Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path](https://mlsanity.com/paper/2106.09923/) (2021)
- [Non-linear Embeddings in Hilbert Simplex Geometry](https://mlsanity.com/paper/2203.11434/) (2022)
- [A Survey on Role-Oriented Network Embedding](https://mlsanity.com/paper/2107.08379/) (2021)
- [Embedding Node Structural Role Identity Using Stress Majorization](https://mlsanity.com/paper/2109.07023/) (2021)
- [Graph-Level Embedding for Time-Evolving Graphs](https://mlsanity.com/paper/2306.01012/) (2023)
- [Unifying Structural Proximity and Equivalence for Enhanced Dynamic Network Embedding](https://mlsanity.com/paper/2503.19926/) (2025)

## Abstract (arXiv)

Recently, there has been an interest in embedding networks in hyperbolic space, since hyperbolic space has been shown to work well in capturing graph/network structure as it can naturally reflect some properties of complex networks. However, the work on network embedding in hyperbolic space has been focused on microscopic node embedding. In this work, we are the first to present a framework to embed the structural roles of nodes into hyperbolic space. Our framework extends struct2vec, a well-known structural role preserving embedding method, by moving it to a hyperboloid model. We evaluated our method on four real-world and one synthetic network. Our results show that hyperbolic space is more effective than euclidean space in learning latent representations for the structural role of nodes.