arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.07907stat.MLcs.LG
收藏

MMD-B-Fair:利用统计检验学习公平表示

MMD-B-Fair: Learning Fair Representations with Statistical Testing

University of British Columbia(不列颠哥伦比亚大学);Amii(阿尔伯塔机器智能研究所)

Namrata Deka, Danica J. Sutherland

AI总结:

提出 MMD-B-Fair,利用核两样本检验与分块检验的渐近性质学习公平表示,在隐藏敏感属性的同时保留目标信息,并在多数据集及下游迁移任务中验证有效。

摘要:

我们提出了一种名为 MMD-B-Fair 的方法,通过核两样本检验来学习数据的公平表示。我们寻找这样的数据神经特征:在这些特征中,最大均值差异(MMD)检验无法区分不同敏感群体的表示,同时保留有关目标属性的信息。最小化 MMD 检验的功效比最大化它(如先前工作所做的那样)更加困难,因为检验阈值的复杂行为不能被简单忽略。我们的方法利用分块检验方案的简单渐近性质,高效地找到公平表示,而无需现有公平表示学习工作中广泛使用的复杂对抗优化或生成建模方案。我们在多个数据集上评估了该方法,展示了其“隐藏”敏感属性信息的能力,以及在下游迁移任务中的有效性。

英文摘要:

We introduce a method, MMD-B-Fair, to learn fair representations of data via kernel two-sample testing. We find neural features of our data where a maximum mean discrepancy (MMD) test cannot distinguish between representations of different sensitive groups, while preserving information about the target attributes. Minimizing the power of an MMD test is more difficult than maximizing it (as done in previous work), because the test threshold's complex behavior cannot be simply ignored. Our method exploits the simple asymptotics of block testing schemes to efficiently find fair representations without requiring complex adversarial optimization or generative modelling schemes widely used by existing work on fair representation learning. We evaluate our approach on various datasets, showing its ability to ``hide'' information about sensitive attributes, and its effectiveness in downstream transfer tasks.

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。

↑