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 2105.14044cs.LGcs.CY
收藏

压缩的公平表示

Fair Representations by Compression

George Mason University(乔治梅森大学)

Xavier Gitiaux, Huzefa Rangwala

摘要:

收集和出售数据的组织因歧视性使用数据而面临越来越多的审查。我们提出了一种新的无监督的方法将数据转换成一个压缩的二进制表示独立的敏感属性。我们表明,在一个信息瓶颈的框架,一个吝啬的表示应该过滤掉敏感属性相关的信息,如果他们直接提供给解码器。实验结果表明,所提出的方法,\textbf{FBC},实现了国家的最先进的准确性和公平性的权衡。对表示比特流的熵的显式控制允许用户沿着速率-失真和速率-公平性曲线平滑且同时地移动。\end{abstract}

英文摘要:

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to transform data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework, a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the proposed method, \textbf{FBC}, achieves state-of-the-art accuracy-fairness trade-off. Explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves. \end{abstract}

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。

↑