论文标题
模块化偏置缓解剂和合奏的实证研究
An Empirical Study of Modular Bias Mitigators and Ensembles
论文作者
论文摘要
有几种偏差缓解剂可以减少机器学习模型中的算法偏差，但是，不幸的是，当在不同的数据拆分中测量时，缓解剂对公平性的影响通常不稳定。一种流行的训练更稳定模型的方法是合奏学习。诸如行李，提升，投票或堆叠之类的合奏已经成功地使预测性能更加稳定。因此，可能会问我们是否可以结合缓解偏见和合奏的优势？为了探讨这个问题，我们首先需要偏见缓解剂和合奏来共同努力。我们构建了一个开源库，可实现10个缓解剂，4个合奏及其相应的超参数的模块化组成。基于此库，我们凭经验探索了13个数据集上组合的空间，包括公平文献中常用的数据集以及我们库新策划的数据集。此外，我们将结果提炼为从业人员的指导图。我们希望本文将有助于改善缓解偏置的稳定性。
There are several bias mitigators that can reduce algorithmic bias in machine learning models but, unfortunately, the effect of mitigators on fairness is often not stable when measured across different data splits. A popular approach to train more stable models is ensemble learning. Ensembles, such as bagging, boosting, voting, or stacking, have been successful at making predictive performance more stable. One might therefore ask whether we can combine the advantages of bias mitigators and ensembles? To explore this question, we first need bias mitigators and ensembles to work together. We built an open-source library enabling the modular composition of 10 mitigators, 4 ensembles, and their corresponding hyperparameters. Based on this library, we empirically explored the space of combinations on 13 datasets, including datasets commonly used in fairness literature plus datasets newly curated by our library. Furthermore, we distilled the results into a guidance diagram for practitioners. We hope this paper will contribute towards improving stability in bias mitigation.
