论文标题
缩小性别工资差距：工作建议中的对抗公平性
Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation
论文作者
论文摘要
这项工作的目的是通过根据求职者的简历提供无偏见的工作建议来帮助减轻已经存在的性别工资差距。我们采用生成的对抗网络来从12m职位空缺文本和900k简历的Word2VEC表示中删除性别偏差。我们的结果表明，由招聘文本创建的表示形式包含算法偏见，而这种偏见会对推荐系统产生现实世界的影响。在没有控制偏见的情况下，建议妇女在我们的数据中薪水明显降低。有了对手公平的代表，这种工资差距消失了，这意味着我们的辩论工作建议减少了工资歧视。我们得出的结论是，单词表示形式的对抗性偏见可以增加系统的现实世界公平性，因此可能是创建公平感知推荐系统的解决方案的一部分。
The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias from word2vec representations of 12M job vacancy texts and 900k resumes. Our results show that representations created from recruitment texts contain algorithmic bias and that this bias results in real-world consequences for recommendation systems. Without controlling for bias, women are recommended jobs with significantly lower salary in our data. With adversarially fair representations, this wage gap disappears, meaning that our debiased job recommendations reduce wage discrimination. We conclude that adversarial debiasing of word representations can increase real-world fairness of systems and thus may be part of the solution for creating fairness-aware recommendation systems.
