sHGCN: Simplified hyperbolic graph convolutional neural networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Arévalo, Pol, Molina, Alexis, Ciudad, Álvaro
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911009611972608
author Arévalo, Pol
Molina, Alexis
Ciudad, Álvaro
author_facet Arévalo, Pol
Molina, Alexis
Ciudad, Álvaro
contents Hyperbolic geometry has emerged as a powerful tool for modeling complex, structured data, particularly where hierarchical or tree-like relationships are present. By enabling embeddings with lower distortion, hyperbolic neural networks offer promising alternatives to Euclidean-based models for capturing intricate data structures. Despite these advantages, they often face performance challenges, particularly in computational efficiency and tasks requiring high precision. In this work, we address these limitations by simplifying key operations within hyperbolic neural networks, achieving notable improvements in both runtime and performance. Our findings demonstrate that streamlined hyperbolic operations can lead to substantial gains in computational speed and predictive accuracy, making hyperbolic neural networks a more viable choice for a broader range of applications.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14438
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle sHGCN: Simplified hyperbolic graph convolutional neural networks
Arévalo, Pol
Molina, Alexis
Ciudad, Álvaro
Machine Learning
Artificial Intelligence
Hyperbolic geometry has emerged as a powerful tool for modeling complex, structured data, particularly where hierarchical or tree-like relationships are present. By enabling embeddings with lower distortion, hyperbolic neural networks offer promising alternatives to Euclidean-based models for capturing intricate data structures. Despite these advantages, they often face performance challenges, particularly in computational efficiency and tasks requiring high precision. In this work, we address these limitations by simplifying key operations within hyperbolic neural networks, achieving notable improvements in both runtime and performance. Our findings demonstrate that streamlined hyperbolic operations can lead to substantial gains in computational speed and predictive accuracy, making hyperbolic neural networks a more viable choice for a broader range of applications.
title sHGCN: Simplified hyperbolic graph convolutional neural networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.14438