ANTIDOTE reweights training examples via a min-min relaxation over an f-divergence neighborhood and claims state-of-the-art accuracy under label noise with near-cross-entropy cost.
Label distributionally robust losses for multi-class classification: Consistency, robustness and adaptivity,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels
ANTIDOTE reweights training examples via a min-min relaxation over an f-divergence neighborhood and claims state-of-the-art accuracy under label noise with near-cross-entropy cost.