MCBM nests concepts hierarchically to enable multi-granularity inference in a single model, reducing expected intervention costs to O(log K) with monotonic performance gains.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 4representative citing papers
Linear mappings in feature space can reconstruct a wide range of image manipulations including semantic edits, suggesting that feature representations are approximately linearly organized.
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
GraphCBMs extend concept bottleneck models by building latent concept graphs to model correlations between concepts, yielding better image classification accuracy, more informative structure for interpretability, and stronger intervention results.
citing papers explorer
-
Matryoshka Concept Bottleneck Models
MCBM nests concepts hierarchically to enable multi-granularity inference in a single model, reducing expected intervention costs to O(log K) with monotonic performance gains.
-
FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
Linear mappings in feature space can reconstruct a wide range of image manipulations including semantic edits, suggesting that feature representations are approximately linearly organized.
-
Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
-
Graph Concept Bottleneck Models
GraphCBMs extend concept bottleneck models by building latent concept graphs to model correlations between concepts, yielding better image classification accuracy, more informative structure for interpretability, and stronger intervention results.