Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model.

Qizhou Wang Bo Han Tongliang Liu Gang Niu Jian Yang Chen Gong

Published in: CoRR (2021)

Keyphrases

probabilistic model
label noise
active learning
bayesian networks
language model
training data
mixture model
noise model
expectation maximization
multiple instance learning
noise tolerant
data mining
genetic algorithm
lower bound