Transfer and Marginalize: Explaining Away Label Noise with Privileged Information. (arXiv:2202.09244v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2202.09244

Supervised learning datasets often have privileged information, in the form
of features which are available at training time but are not available at test
time e.g. the ID of the annotator that provided the label. We argue that
privileged information is useful for explaining away label noise, thereby
reducing the harmful impact of noisy labels. We develop a simple and efficient
method for supervised learning with neural networks: it transfers via weight
sharing the knowledge learned with privileged information and …

arxiv information lg noise transfer