Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
This work addresses robustness in semi-supervised learning for practitioners dealing with biased data, though it is incremental as it builds on existing self-training methods.
The paper tackles the problem of overconfident pseudo-labels in self-training under sample selection bias by proposing a novel confidence measure based on ensemble diversity, resulting in improved performance across multiple datasets and policies.
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 address this issue, we propose a novel confidence measure, called $\mathcal{T}$-similarity, built upon the prediction diversity of an ensemble of linear classifiers. We provide the theoretical analysis of our approach by studying stationary points and describing the relationship between the diversity of the individual members and their performance. We empirically demonstrate the benefit of our confidence measure for three different pseudo-labeling policies on classification datasets of various data modalities. The code is available at https://github.com/ambroiseodt/tsim.