Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders
This work addresses the under-explored area of unsupervised hyperbolic embeddings for hierarchical data, offering a novel method that could benefit tasks like network analysis.
The paper tackles the problem of unsupervised representation learning in hyperbolic spaces for hierarchical data, proposing a hyperbolic message passing auto-encoder and validating its benefits through analyses.
Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit from learned representations in hyperbolic space. To explore how well the hierarchical structure of unlabeled data can be represented in hyperbolic spaces, we design a novel hyperbolic message passing auto-encoder whose overall auto-encoding is performed in hyperbolic space. The proposed model conducts auto-encoding the networks via fully utilizing hyperbolic geometry in message passing. Through extensive quantitative and qualitative analyses, we validate the properties and benefits of the unsupervised hyperbolic representations. Codes are available at https://github.com/junhocho/HGCAE.