Fair Allocation Over Time, with Applications to Content Moderation

Fair Allocation Over Time, with Applications to Content Moderation
复制标题

随着时间的推移公平分配,以及内容审核的应用

DOI:
10.1145/3580305.3599340
复制
发表时间:
2023
期刊:
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
影响因子:
--
通讯作者:
Stier-Moses, Nicolas
Stier-Moses, Nicolas
中科院分区:
--
文献类型:
--
作者:
Allouah, Amine;Kroer, Christian;Zhang, Xuan;Avadhanula, Vashist;Bohanon, Nona;Dania, Anil;Gocmen, Caner;Pupyrev, Sergey;Shah, Parikshit;Stier-Moses, Nicolas

文献摘要

参考文献

被引文献

相似文献

在当今的数字世界中,与在线平台的互动无处不在,因此内容审核对于保护用户免受不符合预先建立的社区指导方针的内容的影响非常重要。考虑到每天在线生成的大量内容,在计划的每个阶段都有一个有效的内容审核系统尤为重要。我们研究了将人类内容审查员分配到不同有害内容类别的短期规划问题。我们利用公平分配的工具,研究了竞争均衡和leximin分配规则的应用来解决这一问题。在传统的费舍尔市场设置之上,我们还纳入了具有实际重要性的新方面。第一个方面是不同内容类别的预测工作负载,这对规划器选择的分配施加了约束。我们展示了受著名的Eisenberg-Gale程序启发的公式如何使我们找到一种分配,这种分配不仅满足预测的工作量,而且还公平地将内容审稿人的剩余工作时间分配给所有内容类别。在实际工作负载偏离预测工作负载的情况下,公平地分配供应过剩提供了保障。第二个实际考虑是与时间相关的分配,其动机是合作伙伴需要为审查人员提供跨天的调度指导,以实现效率。为了解决时间组件,我们为单时间段设置引入了各种公平分配方法的新扩展,并展示了许多属性在本质上进行了扩展,尽管进行了一些修改。最后,与时间部分相关,我们还研究了如何满足市场对平稳分配的渴望(即,每次分配的变化不大),以便最大限度地减少人员配置的切换。我们通过从Meta获得的真实数据证明了我们提出的方法的性能。
In today's digital world, interaction with online platforms is ubiquitous, and thus content moderation is important for protecting users from content that do not comply with pre-established community guidelines. Given the vast volume of content generated online daily, having an efficient content moderation system throughout every stage of planning is particularly important. We study the short-term planning problem of allocating human content reviewers to different harmful content categories. We use tools from fair division and study the application of competitive equilibrium and leximin allocation rules for addressing this problem. On top of the traditional Fisher market setup, we additionally incorporate novel aspects that are of practical importance. The first aspect is the forecasted workload of different content categories, which puts constraints on the allocation chosen by the planner. We show how a formulation that is inspired by the celebrated Eisenberg-Gale program allows us to find an allocation that not only satisfies the forecasted workload, but also fairly allocates the remaining working hours from the content reviewers among all content categories. A fair allocation of oversupply provides a guardrail in cases where the actual workload deviates from the predicted workload. The second practical consideration is time dependent allocation that is motivated by the fact that partners need scheduling guidance for the reviewers across days to achieve efficiency. To address the time component, we introduce new extensions of the various fair allocation approaches for the single-time period setting, and we show that many properties extend in essence, albeit with some modifications. Lastly, related to the time component, we additionally investigate how to satisfy markets' desire for smooth allocation (i.e, an allocation that does not vary much from time to time) so that the switch in staffing is minimized. We demonstrate the performance of our proposed approaches through real-world data obtained from Meta.
评价嘈杂的多臂强盗 Top K 排名
DOI: --
发表时间: 2021
期刊: International Conference on Artificial Intelligence and Statistics
影响因子: --
作者:
Evrard Garcelon;Vashist Avadhanula;A. Lazaric;and Matteo Pirotta
通讯作者: and Matteo Pirotta
不可分割的物品和家务的分配几乎没有群体嫉妒
DOI: --
发表时间: 2019
期刊: International Joint Conference on Artificial Intelligence
影响因子: --
作者:
H. Aziz;Simon Rey
通讯作者: Simon Rey
DOI: 10.2307/2288164
发表时间: 1983-09
影响因子: 3.7
作者:
K. Arrow;M. Intriligator
通讯作者: K. Arrow;M. Intriligator
艾森伯格-盖尔市场:算法和博弈论属性
DOI: 10.1016/j.geb.2008.11.011
发表时间: 2010
期刊: Games Econ. Behav.
影响因子: --
作者:
K. Jain;V. Vazirani
通讯作者: V. Vazirani
QUEST:大规模内容审核的队列模拟
DOI: --
发表时间: 2021
期刊: arXiv.org
影响因子: --
作者:
Rahul M. Makhijani;P. Shah;Vashist Avadhanula;C. Gocmen;N. Stier;Julián Mestre
通讯作者: Julián Mestre