Hyperbolic Graph Embedders for Link Prediction and Topology Reconstruction
Not on the map. Why?
Abstract (arXiv)
Hyperbolic embeddings provide compact geometric representations of complex networks in hyperbolic spaces, but systematic comparisons of methods developed in machine learning, network science, and algorithmics remain rare. We benchmark 13 unsupervised hyperbolic graph embedders under a unified protocol for link prediction and topology reconstruction on synthetic and empirical networks. The protocol captures both missing-link recovery and the preservation of local and global network structure. Maximum-likelihood and representation-learning-based approaches, including hybrid variants, achieve the strongest overall performance, although no method dominates across all tasks and structural regimes. Performance is more strongly associated with embedding paradigm than with disciplinary origin. We identify the network regimes in which different paradigms succeed or fail and provide practical guidance for method selection in downstream applications.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 50 references that are in the map. First posted on arXiv 7 Aug 2026.
Builds on
16 of 50 references.
References · 16
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
- 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
- 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
- 2022GraphWorld: Fake Graphs Bring Real Insights for GNNscited by 56
- 2020Network Geometrycited by 31
- 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
- 2016Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic spacecited by 21
- 2021Systematic comparison of graph embedding methods in practical taskscited by 11
- 2019Mercator: uncovering faithful hyperbolic embeddings of complex networkscited by 10
- 2015Network Geometry Inference using Common Neighborscited by 8
- 2019Link prediction with hyperbolic geometrycited by 7
4 more
- 2017A nonuniform popularity-similarity optimization (nPSO) model to efficiently generate realistic complex networks with communitiescited by 6
- 2019Efficiently Generating Geometric Inhomogeneous and Hyperbolic Random Graphscited by 2
- 2021Discrete Hyperbolic Random Graph Modelcited by 1
- 2024Modelling brain connectomes networks: Solv is a worthy competitor to hyperbolic geometry!cited by 1
Built on by
Not cited yet.