The Geometry-Aware Generative Autoencoder (GAGA) constructs a neural network embedding space that respects intrinsic geometries discovered by manifold learning and learns a warped Riemannian metric derived from both points on the data manifold and negative samples off the manifold.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• artificial neural networks concept