Recommender system fairness has been studied from the perspectives of a variety of stakeholders including content producers, the content itself and recipients of recommendations. Regardless of which type of stakeholders are considered, most works in this area assess the efficacy of fairness intervention by evaluating a single fixed fairness criterion through the lens of a one-shot, static setting. Yet recommender systems constitute dynamical systems with feedback loops from the recommendations to the underlying population distributions which could lead to unforeseen and adverse consequences if not taken into account. In this paper, we study a connection recommender system patterned after the systems employed by web-scale social networks and analyze the long-term effects of intervening on fairness in the recommendations. We find that, although seemingly fair in aggregate, common exposure and utility parity interventions fail to mitigate amplification of biases in the long term. We theoretically characterize how certain fairness interventions impact the bias amplification dynamics in a stylized P\'{o}lya urn model.
翻译:从包括内容制作者、内容本身和建议接受者在内的各种利益攸关方的角度,对建议系统公平性进行了研究。无论考虑的是哪类利益攸关方,大多数在这一领域开展工作,通过一次性静态设置的镜头评估单一固定公平标准来评估公平性干预的效力。然而,建议系统构成动态系统,从建议到基本人口分布的反馈回路,如果不加以考虑,可能导致意外和不利的后果。在本文中,我们研究一种参照网络规模社会网络使用的系统的模式的连接建议系统,并分析干预对建议公平性的长期影响。我们发现,尽管总体来看看似公平,共同暴露和效用均等干预措施未能减少长期偏见的扩大。我们从理论上判断某些公平干预措施如何影响Stylized P\{o}lya urn 模型中的偏见放大动态。