2021/03/29 by Jiwoong Park, Junho Cho, Park, Jiwoong +5 · 2 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Speech Recognition and Synthesis
paper · pdf · doi:10.48550/arxiv.2103.16046
openalex publication_date 2021/03/29 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Most of the existing literature regarding hyperbolic embedding concentrate\nupon supervised learning, whereas the use of unsupervised hyperbolic embedding\nis less well explored. In this paper, we analyze how unsupervised tasks can\nbenefit from learned representations in hyperbolic space. To explore how well\nthe hierarchical structure of unlabeled data can be represented in hyperbolic\nspaces, we design a novel hyperbolic message passing auto-encoder whose overall\nauto-encoding is performed in hyperbolic space. The proposed model conducts\nauto-encoding the networks via fully utilizing hyperbolic geometry in message\npassing. Through extensive quantitative and qualitative analyses, we validate\nthe properties and benefits of the unsupervised hyperbolic representations.\nCodes are available at https://github.com/junhocho/HGCAE.\n