Sign in

Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap

By Théo Uscidda and others
Learning disentangled representations in an unsupervised manner is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. While remarkably difficult to solve in general, recent works have shown that disentanglement is provably achievable under additional assumptions that can leverage geometrical constraints,... Show more
July 10, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap
Click on play to start listening