mlsanityData to 14 Oct 2026

On original and latent space connectivity in deep neural networks

arXiv 2311.06816 ↗First posted 12 Nov 2023cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We study whether inputs from the same class can be connected by a continuous path, in original or latent representation space, such that all points on the path are mapped by the neural network model to the same class. Understanding how the neural network views its own input space and how the latent spaces are structured has value for explainability and robustness. We show that paths, linear or nonlinear, connecting same-class inputs exist in all cases studied.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 12 Nov 2023.

Builds on

21 of 26 references.

References · 21

  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  3. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
  4. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 588
  5. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  6. 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
  7. 2018Essentially No Barriers in Neural Network Energy Landscapecited by 330
  8. 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
  9. 2016Exponential expressivity in deep neural networks through transient chaoscited by 261
  10. 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
  11. 2017Generalization in Deep Learningcited by 146
  12. 2022Reconstructing Training Data from Trained Neural Networkscited by 133
9 more
  1. 2016Topology and Geometry of Half-Rectified Network Optimizationcited by 102
  2. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  3. 2017Classification and Geometry of General Perceptual Manifoldscited by 62
  4. 2019Dimensionality compression and expansion in Deep Neural Networkscited by 38
  5. 2022Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Explorationcited by 21
  6. 2019NormLime: A New Feature Importance Metric for Explaining Deep Neural Networkscited by 16
  7. 2022Effects of Data Geometry in Early Deep Learningcited by 12
  8. 2023Deep neural networks architectures from the perspective of manifold learningcited by 5
  9. 2020Classify and Generate: Using Classification Latent Space Representations for Image Generationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attentioncited by 3