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.

翻译：自训练是半监督学习中一种广为人知的方法。它通过迭代方式，为模型置信度高的未标注数据分配伪标签，并将其视为标注样本处理。对于神经网络而言，softmax预测概率常被用作置信度度量，尽管已知其在错误预测时也会表现出过度自信。这一现象在样本选择偏差（即数据标注受限于某些约束）存在时尤为加剧。为解决该问题，我们提出了一种新颖的置信度度量方法——$\mathcal{T}$-相似度，该方法基于线性分类器集成的预测多样性构建。我们通过研究驻点并描述各成员多样性与其性能之间的关系，对所提方法进行了理论分析。我们实证证明了该置信度度量在三种不同伪标签策略下，对多种数据模态的分类数据集均具有优势。代码开源于 https://github.com/ambroiseodt/tsim。