EchoAlign adjusts instances with controllable generative models to match noisy labels and selects reliable subsets, outperforming prior methods on benchmarks especially under 30% instance-dependent noise.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · external index
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels
EchoAlign adjusts instances with controllable generative models to match noisy labels and selects reliable subsets, outperforming prior methods on benchmarks especially under 30% instance-dependent noise.