arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.00106cs.LGcs.AIcs.CY
收藏

在深度学习中实现公平的可感知性

Towards Auditability for Fairness in Deep Learning

Konya Technical University(科尼亚技术大学);University of Vermont(佛蒙特大学)

Ivoline C. Ngong, Krystal Maughan, Joseph P. Near

摘要:

群体公平性指标可以检测到深度学习模型在弱势群体和弱势群体中的行为是否不同,但即使是在这些指标上得分很高的模型也会做出明显不公平的预测。我们提出了平滑预测灵敏度,这是一种有效计算的深度学习模型的个体公平性度量,其灵感来自深度学习中的可解释性。平滑的预测灵敏度允许对各个预测进行公平性审核。我们提出了初步的实验结果表明,平滑的预测灵敏度可以帮助区分公平和不公平的预测,它可能有助于检测公然不公平的预测从“组公平”的模型。

英文摘要:

Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions. We present smooth prediction sensitivity, an efficiently computed measure of individual fairness for deep learning models that is inspired by ideas from interpretability in deep learning. smooth prediction sensitivity allows individual predictions to be audited for fairness. We present preliminary experimental results suggesting that smooth prediction sensitivity can help distinguish between fair and unfair predictions, and that it may be helpful in detecting blatantly unfair predictions from "group-fair" models.

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。

↑