AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning

Seunghyuk Cho, Juyong Lee, Jaesik Park, Dongwoo Kim

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Tractable probabilistic models · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Rotate the covariance toward the mean direction rather than use full-covariance HWNHyperbolic VAE · Noisy synthetic binary tree, depth 5Correlation w/ depth: 0.878_{\pm 0.051} -> 0.911_{\pm 0.027}Improved
Rotate the covariance toward the mean direction rather than use diagonal HWNHyperbolic VAE · Noisy synthetic binary tree, depth 6Correlation w/ distance: 0.817_{\pm 0.010} -> 0.822_{\pm 0.017}No clear effect
Use RoWN rather than full-covariance HWNProbabilistic hyperbolic word embedding · WordNet, latent dimension 10MR: 466.513_{\pm 75.142} -> 2.888_{\pm 0.162}Improved
Use RoWN rather than diagonal HWNProbabilistic hyperbolic word embedding · WordNet, latent dimension 20mAP: 0.905_{\pm 0.007} -> 0.921_{\pm 0.005}Improved
Use RoWN rather than isotropic HWNHyperbolic VAE · Atari 2600 Breakout, latent dimension 20Correlation btw. score and norm: 0.607_{\pm 0.015} -> 0.561_{\pm 0.029}Hurt
Learn the rotation direction instead of fixing it toward the mean (ablation)RoWN · Noisy synthetic binary tree, depth 7Correlation w/ depth: 0.827_{\pm 0.047} -> 0.711_{\pm 0.072}Hurt
Learn the rotation direction instead of fixing it toward the mean (ablation)RoWN · Noisy synthetic binary tree, depth 4Correlation w/ depth: 0.930_{\pm 0.026} -> 0.952_{\pm 0.018}Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy