arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11338cs.LGcs.AIcs.CYstat.ML
收藏

具有部分反馈的公平分类:一种基于探索的数据收集方法

Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach

Duke University(杜克大学);Yale University(耶鲁大学)

Vijay Keswani, Anay Mehrotra, L. Elisa Celis

AI总结:

提出一种基于探索的数据收集方法,通过探索策略收集被忽略子群体的结果数据,保证子群体覆盖、限制假阳性并收敛至理想分类器,在提升各群体真阳性比例的同时仅微小降低预测效用。

摘要:

在许多预测场景中(如信贷放款),真实结果仅对过去被正向分类的样本可观测。这些过去的观测数据反过来构成了用于进行未来预测的分类器的训练数据集。然而,此类训练数据集缺乏关于过去被(错误地)负向分类的样本结果的信息,并可能导致错误的分类器。我们提出了一种方法,该方法使用可用数据训练分类器,并附带一系列探索策略,用于收集关于原本会被忽略的子群体的结果数据。对于任何探索策略,该方法均提供以下保证:(1)所有子群体均被探索;(2)假阳性比例受到限制;(3)训练的分类器收敛于一个“理想的”分类器。正确的探索策略取决于具体场景;可以选择该策略以改善学习保证并编码特定场景的群体公平性属性。在真实世界数据集上的评估表明,该方法持续提升收集结果数据的质量,并改善所有群体的真阳性比例,仅带来预测效用的微小下降。

英文摘要:

In many predictive contexts (e.g., credit lending), true outcomes are only observed for samples that were positively classified in the past. These past observations, in turn, form training datasets for classifiers that make future predictions. However, such training datasets lack information about the outcomes of samples that were (incorrectly) negatively classified in the past and can lead to erroneous classifiers. We present an approach that trains a classifier using available data and comes with a family of exploration strategies to collect outcome data about subpopulations that otherwise would have been ignored. For any exploration strategy, the approach comes with guarantees that (1) all sub-populations are explored, (2) the fraction of false positives is bounded, and (3) the trained classifier converges to a ``desired'' classifier. The right exploration strategy is context-dependent; it can be chosen to improve learning guarantees and encode context-specific group fairness properties. Evaluation on real-world datasets shows that this approach consistently boosts the quality of collected outcome data and improves the fraction of true positives for all groups, with only a small reduction in predictive utility.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑