Introduces coherence as a topological constraint on representations and the Coh objective to enforce geometric clustering for interpretability in neural networks.
Guibas, and Steve Y
4 Pith papers cite this work, alongside 423 external citations. Polarity classification is still indexing.
4
Pith papers citing it
423
external citations · external index
representative citing papers
PLACE delivers a closed-form certified classification method for point clouds and graphs based on persistent homology with explicit excess-risk bounds, selection rules, and training-time certificates.
Interleaving-distance confidence regions for Reeb graphs are obtained from PL proximity-graph estimators, with Mapper treated as a controlled visualization coarsening and extended persistence bounded by twice the interleaving distance.
Presents ILP formulations to bound the interleaving distance on mapper graphs, with evaluation on small examples and benchmark datasets.
citing papers explorer
-
Learning Coherent Representations: A Topological Approach to Interpretability
Introduces coherence as a topological constraint on representations and the Coh objective to enforce geometric clustering for interpretability in neural networks.
-
A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification
PLACE delivers a closed-form certified classification method for point clouds and graphs based on persistent homology with explicit excess-risk bounds, selection rules, and training-time certificates.
-
Building confidence regions for Reeb graphs using the interleaving distance
Interleaving-distance confidence regions for Reeb graphs are obtained from PL proximity-graph estimators, with Mapper treated as a controlled visualization coarsening and extended persistence bounded by twice the interleaving distance.
-
Towards an Optimal Bound for the Interleaving Distance on Mapper Graphs
Presents ILP formulations to bound the interleaving distance on mapper graphs, with evaluation on small examples and benchmark datasets.