Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zhangyu, Xu, Lantian, Kong, Zhifeng, Wang, Weilong, Peng, Xuyu, Zheng, Enyang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.16641
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916333866713088
author Wang, Zhangyu
Xu, Lantian
Kong, Zhifeng
Wang, Weilong
Peng, Xuyu
Zheng, Enyang
author_facet Wang, Zhangyu
Xu, Lantian
Kong, Zhifeng
Wang, Weilong
Peng, Xuyu
Zheng, Enyang
contents Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, learning hyperbolic embeddings of hierarchical data is difficult due to the different geometry between hyperbolic space and the Euclidean space. To address such difficulties, we first categorize three kinds of illness that harm the performance of the embeddings. Then, we develop a geometry-aware algorithm using a dilation operation and a transitive closure regularization to tackle these illnesses. We empirically validate these techniques and present a theoretical analysis of the mechanism behind the dilation operation. Experiments on synthetic and real-world datasets reveal superior performances of our algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16641
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
Wang, Zhangyu
Xu, Lantian
Kong, Zhifeng
Wang, Weilong
Peng, Xuyu
Zheng, Enyang
Machine Learning
Artificial Intelligence
Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, learning hyperbolic embeddings of hierarchical data is difficult due to the different geometry between hyperbolic space and the Euclidean space. To address such difficulties, we first categorize three kinds of illness that harm the performance of the embeddings. Then, we develop a geometry-aware algorithm using a dilation operation and a transitive closure regularization to tackle these illnesses. We empirically validate these techniques and present a theoretical analysis of the mechanism behind the dilation operation. Experiments on synthetic and real-world datasets reveal superior performances of our algorithm.
title A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.16641