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.
Graph contrastive learning with augmentations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.