HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
Y., KALROA., CHAUD
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
A user study for an MTG Commander dashboard finds players prefer outcome-driven metrics and canonical charts like heatmaps over complex visualizations, stressing customization and contextual views.
citing papers explorer
-
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
-
Building a Data Dashboard for Magic: The Gathering: Initial Design Considerations
A user study for an MTG Commander dashboard finds players prefer outcome-driven metrics and canonical charts like heatmaps over complex visualizations, stressing customization and contextual views.