Recommender system has intrinsic problems such as sparsity and fairness. Although it has been widely adopted for the past decades, research on fairness of recommendation algorithms has been largely neglected until recently. One important paradigm for resolving the issue is regularization. However, researchers have not been able to come up with a consensusly agreed regularization term like regularization framework in other fields such as Lasso or Ridge Regression. In this paper, we borrow concepts from information geometry and propose a new regularization-based fair algorithm called KL-Mat. The algorithmic technique leads to a more robust performance in accuracy performance such as MAE. More importantly, the algorithm produces much fairer results than vanilla matrix factorization approach. KL-Mat is fast, easy-to-implement and explainable.
翻译:推荐人系统存在诸如宽度和公平性等内在问题。 尽管过去几十年来它已被广泛采用,但直到最近,关于建议算法公平性的研究在很大程度上一直被忽略。解决该问题的一个重要范例是规范化。然而,研究人员未能在Lasso或Ridge Regresion等其他领域形成一个协商一致商定的正规化术语,如正规化框架。在本文中,我们从信息几何学中借用了概念,并提出了一个新的基于正规化的公平算法,称为KL-Mat。算法技术导致像MAE这样的精准性能表现更加稳健。更重要的是,算法比香草矩阵因子化方法产生更公平的结果。 KL-Mat是快速、易于执行和可以解释的。