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.
Dirichlet-based per-sample weighting by transi- tion matrix for noisy label learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.