Skip to yearly menu bar Skip to main content


GeomCA: Geometric Evaluation of Data Representations

Petra Poklukar · Anastasiia Varava · Danica Kragic

Keywords: [ Embedding and Representation learning ]


Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.

Chat is not available.