SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.06070 · ICML · 2022

Quantifying and Learning Linear Symmetry-Based Disentanglement

Loek Tonnaer, Luis Rey, Vlado Menkovski, Mike Holenderski, Jacobus Portegies

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD. Such a metric is crucial to evaluate LSBD methods and to compare to previous understandings of disentanglement. We propose D LSBD , a mathematically sound metric to quantify LSBD, and provide a practical implementation for SO(2) groups. Furthermore, from this metric we derive LSBD-VAE, a semi-supervised method to learn LSBD representations. We demonstrate 1 the utility of our metric by showing that (1) common VAE-based disentanglement methods don't learn LSBD representations, (2) LSBD-VAE, as well as other recent methods, can learn LSBD representations needing only limited supervision on transformations, and (3) various desirable properties expressed by existing disentanglement metrics are also achieved by LSBD representations.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2011.06070")
get_code_for_paper("2011.06070")
have("2011.06070")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2011.06070.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2011.06070.svg)](https://syntology.ai/paper/2011.06070)

Connect an agent — have() is free.