HCBM apply Hoeffding functional decomposition to concept scores for non-linear sparse predictions in CBMs, with claimed robustness to leakage and strong results on overhead image tasks.
hooked seabird beak
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hoeffding Concept Bottleneck Models with Applications to Overhead Images
HCBM apply Hoeffding functional decomposition to concept scores for non-linear sparse predictions in CBMs, with claimed robustness to leakage and strong results on overhead image tasks.