Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited. Although it is often established that the average accuracy for the entire population of data is improved, it is unclear how SSL fares with different sub-populations. Understanding the above question has substantial fairness implications when different sub-populations are defined by the demographic groups that we aim to treat fairly. In this paper, we reveal the disparate impacts of deploying SSL: the sub-population who has a higher baseline accuracy without using SSL (the "rich" one) tends to benefit more from SSL; while the sub-population who suffers from a low baseline accuracy (the "poor" one) might even observe a performance drop after adding the SSL module. We theoretically and empirically establish the above observation for a broad family of SSL algorithms, which either explicitly or implicitly use an auxiliary "pseudo-label". Experiments on a set of image and text classification tasks confirm our claims. We introduce a new metric, Benefit Ratio, and promote the evaluation of the fairness of SSL (Equalized Benefit Ratio). We further discuss how the disparate impact can be mitigated. We hope our paper will alarm the potential pitfall of using SSL and encourage a multifaceted evaluation of future SSL algorithms.

翻译：半监督学习（SSL）在高质量监督数据严重受限的情况下，已展现出提升多种学习任务模型准确率的潜力。尽管普遍确认其对整体数据集的平均准确率有所提升，但SSL在不同子群体中的表现尚不明确。当子群体由我们旨在公平对待的人口统计群体界定时，理解上述问题具有显著的公平性意义。本文揭示了部署SSL的不平等影响：未使用SSL时基线准确率较高的子群体（“富者”）倾向于从SSL中获益更多；而基线准确率较低的子群体（“穷者”）在添加SSL模块后甚至可能出现性能下降。我们从理论和实证层面验证了上述观察结果，涵盖广泛使用显式或隐式辅助“伪标签”的SSL算法家族。在图像和文本分类任务上的实验证实了我们的主张。我们引入新指标“收益比”，并推动SSL公平性评估（均衡收益比）。进一步探讨了缓解不平等影响的可能方法。希望本文能警示SSL的潜在陷阱，并鼓励对未来的SSL算法进行多维度评估。