Controlling Fairness and Bias in Dynamic Learning-to-Rank
Controlling Fairness and Bias in Dynamic Learning-to-Rank
复制标题
DOI：
10.1145/3397271.3401100
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Marco Morik;Ashudeep Singh;Jessica Hong;T. Joachims
中科院分区：
文献类型：
--
作者：
Marco Morik;Ashudeep Singh;Jessica Hong;T. Joachims
排名是许多在线平台将用户与项目（例如新闻，产品，音乐，视频）相匹配的主要界面。在这些双边市场中，不仅用户从排名中获得效用，而且排名还决定了项目提供商（例如出版商，卖家，艺术家，工作室）的效用（例如曝光，收入）。我们已经注意到，短视地优化用户的效用--就像几乎所有的学习排名算法所做的那样--可能对物品提供者不公平。因此，我们提出了一种学习排名的方法，明确执行基于价值的公平保证组的项目（例如，由同一出版商的文章，由同一艺术家的轨道）。特别是，我们提出了一个学习算法，确保摊销组公平的概念，同时学习隐式反馈数据的排名功能。该算法采用控制器的形式，它集成了公平性和实用性的无偏估计，随着更多的数据变得可用，动态地适应两者。除了其严格的理论基础和收敛保证，我们发现经验，该算法是非常实用和强大的。
Rankings are the primary interface through which many online platforms match users to items (e.g. news, products, music, video). In these two-sided markets, not only the users draw utility from the rankings, but the rankings also determine the utility (e.g. exposure, revenue) for the item providers (e.g. publishers, sellers, artists, studios). It has already been noted that myopically optimizing utility to the users -- as done by virtually all learning-to-rank algorithms -- can be unfair to the item providers. We, therefore, present a learning-to-rank approach for explicitly enforcing merit-based fairness guarantees to groups of items (e.g. articles by the same publisher, tracks by the same artist). In particular, we propose a learning algorithm that ensures notions of amortized group fairness, while simultaneously learning the ranking function from implicit feedback data. The algorithm takes the form of a controller that integrates unbiased estimators for both fairness and utility, dynamically adapting both as more data becomes available. In addition to its rigorous theoretical foundation and convergence guarantees, we find empirically that the algorithm is highly practical and robust.