mlsanityData to 7 Oct 2026

GeomCA: Geometric Evaluation of Data Representations

arXiv 2105.12486 ↗First posted 26 May 2021cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 26 May 2021.

Builds on

18 of 31 references.

References · 18

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  5. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  6. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  7. 2018Disentangling by Factorisingcited by 614
  8. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  9. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  10. 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
  11. 2019Topological Autoencoderscited by 124
  12. 2018Geometry Score: A Method For Comparing Generative Adversarial Networkscited by 56
6 more
  1. 2020Geometrically Enriched Latent Spacescited by 45
  2. 2020Representations for Stable Off-Policy Reinforcement Learningcited by 31
  3. 2020Disentangling by Subspace Diffusioncited by 28
  4. 2020Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulationcited by 25
  5. 2020Unsupervised Representation Learning by InvariancePropagationcited by 18
  6. 2020Data-efficient visuomotor policy training using reinforcement learning and generative modelscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 1.

9 papers.

  1. 2022Geometric Multimodal Contrastive Representation Learningcited by 40
  2. 2022Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shiftscited by 16
  3. 2023TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Modelscited by 13
  4. 2023Topological Pooling on Graphscited by 9
  5. 2021How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agentscited by 6
  6. 2022Delaunay Component Analysis for Evaluation of Data Representationscited by 6
  7. 2024Hyperbolic Delaunay Geometric Alignmentcited by 2
  8. 2022Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Modelscited by 1
  9. 2022GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphscited by 0