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 2305.01141cs.IR
收藏

论文推荐中的多维公平性

Multidimensional Fairness in Paper Recommendation

Reem Alsaffar, Susan Gauch, Hiba Al-Kawaz

AI总结:

针对论文推荐算法中的隐性偏见问题,提出三种同时兼顾多维度作者人口特征的公平推荐方法,实验证明其能在基本不降低效用的前提下显著提升多样性,可推广至多类学术遴选场景。

摘要:

为防止会议和期刊论文评审与遴选过程中可能存在的偏见,多数机构采用双盲评审。尽管如此,研究表明偏见仍然存在。用于论文评审的推荐算法也可能存在隐性偏见。我们提出了三种专门考虑作者多样性的公平论文推荐方法来解决这一问题。与仅使用单一受保护变量的典型公平算法不同,我们的方法可同时在多个受保护变量上实现公平结果。我们的多维作者档案包含五个人口统计特征:性别、种族、职业阶段、大学排名和地理位置。整体多样性(Overall Diversity)方法使用整体多样性得分对论文进行排序。循环多样性(Round Robin Diversity)技术轮流从每个受保护群体的作者中选择论文,而多面多样性(Multifaceted Diversity)方法则优先选择能填补最重要人口统计特征缺口的论文。我们对比了基于布尔特征和连续值特征的作者多样性档案的效果。我们从SIGCHI 2017、DIS 2017和IUI 2017的论文池中选取论文,为SIGCHI 2017推荐论文,并利用用户档案评估这些算法。我们将推荐的论文与会议实际选中的论文进行了对比。研究发现,无论使用布尔特征值还是连续特征值的档案,三种技术都能提升多样性,而效用仅略有下降或没有下降。我们表现最佳的技术Multifaceted Diversity,通过选择多样性提升42.50%且效用提高2.45%的作者,推荐了一组符合人口统计均等的论文。该策略可应用于资助提案遴选、会议论文、期刊论文及其他学术工作场景。

英文摘要:

To prevent potential bias in the paper review and selection process for conferences and journals, most include double blind review. Despite this, studies show that bias still exists. Recommendation algorithms for paper review also may have implicit bias. We offer three fair methods that specifically take into account author diversity in paper recommendation to address this. Our methods provide fair outcomes across many protected variables concurrently, in contrast to typical fair algorithms that only use one protected variable. Five demographic characteristics-gender, ethnicity, career stage, university rank, and geolocation-are included in our multidimensional author profiles. The Overall Diversity approach uses a score for overall diversity to rank publications. The Round Robin Diversity technique chooses papers from authors who are members of each protected group in turn, whereas the Multifaceted Diversity method chooses papers that initially fill the demographic feature with the highest importance. We compare the effectiveness of author diversity profiles based on Boolean and continuous-valued features. By selecting papers from a pool of SIGCHI 2017, DIS 2017, and IUI 2017 papers, we recommend papers for SIGCHI 2017 and evaluate these algorithms using the user profiles. We contrast the papers that were recommended with those that were selected by the conference. We find that utilizing profiles with either Boolean or continuous feature values, all three techniques boost diversity while just slightly decreasing utility or not decreasing. By choosing authors who are 42.50% more diverse and with a 2.45% boost in utility, our best technique, Multifaceted Diversity, suggests a set of papers that match demographic parity. The selection of grant proposals, conference papers, journal articles, and other academic duties might all use this strategy.

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。

↑