Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias

arXiv:2310.14814v3 Announce Type: replace
Abstract: Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax prediction probabilities are often used as a confidence measure, although they are known to be overconfident, even for wrong predictions. This phenomenon is particularly intensified in the presence of sample selection bias, i.e., when data labeling is subject to some constraint. To …

arxiv bias cs.ai cs.lg diversity ensemble robust sample self-training stat.ml training type