cs.LGDec 8, 2025

HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability

Authors: Sudhanva Manjunath Athreya, Paul Rosen

Organizations: University of Utah

Abstract

Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of Latent Embeddings), a method for analyzing and interpreting discriminative neural networks through persistent homology. HOLE extracts topological features from intermediate activations and presents them using a suite of visualization techniques, including cluster flow diagrams, blob graphs, and heatmap dendrograms. These tools facilitate the examination of representation structure and quality across layers. We evaluate HOLE using a range of discriminative models, focusing on representation quality, interpretability across layers, and robustness to input perturbations and model compression. The results indicate that topological analysis reveals patterns associated with class separation, feature disentanglement, and model robustness, providing a complementary perspective for understanding and improving deep learning systems.

Figures & tables

Appendix figures & tables34 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DUNE: Disentangling Polysemantic Neurons Without Losing Predictive Performance

    May 29, 2026Doğukan Bağcı, Bernt Schiele, Simone Schaub-Meyer +2Disentangled Representation LearningRepresentation Disentanglement

  2. Post-Hoc Feature Selection Layer for Neural Networks Interpretability

    Oct 22, 2026João Kenji Suwa, João Pedro Silveira e Silva, Bruno Iochins GrisciNeural Network InterpretabilityFeature Attribution

  3. The Polytopal Neural Network

    Oct 8, 2026A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2Neural Network InterpretabilityGeometric Representation Learning