arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01846cs.LG
收藏

图模型与作为公平正则化子的公平I-投影之间的KL-发散性

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

Ghent University(根特大学)

Maarten Buyl, Tijl De Bie

摘要:

图上的学习和推理越来越多地借助于概率模型来完成,例如指数随机图模型、图嵌入模型和图神经网络。然而,当图表对人与人之间的关系进行建模时,它们将不可避免地反映出偏见、偏见和其他形式的不公平和不平等。因此,一个重要的挑战是设计准确的图建模方法,同时根据问题所需的特定公平性概念来保证公平性。然而,过去关于这个主题的工作仍然很少,仅限于消除特定的图建模方法,并且通常旨在以间接的方式确保公平性。我们提出了一个通用的方法适用于大多数概率图建模方法。具体来说,我们首先定义的类的公平图模型对应于一组选定的公平标准。考虑到这一点,我们提出了一个公平正则化定义为KL之间的发散图模型和它的I-投影到一组公平的模型。我们证明,使用这种公平性正则化与现有的图建模方法相结合,有效地权衡公平性与准确性,而最先进的模型只能使这种权衡的公平性标准,他们是专门设计的。

英文摘要:

Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they will inevitably reflect biases, prejudices, and other forms of inequity and inequality. An important challenge is thus to design accurate graph modeling approaches while guaranteeing fairness according to the specific notion of fairness that the problem requires. Yet, past work on the topic remains scarce, is limited to debiasing specific graph modeling methods, and often aims to ensure fairness in an indirect manner. We propose a generic approach applicable to most probabilistic graph modeling approaches. Specifically, we first define the class of fair graph models corresponding to a chosen set of fairness criteria. Given this, we propose a fairness regularizer defined as the KL-divergence between the graph model and its I-projection onto the set of fair models. We demonstrate that using this fairness regularizer in combination with existing graph modeling approaches efficiently trades-off fairness with accuracy, whereas the state-of-the-art models can only make this trade-off for the fairness criterion that they were specifically designed for.

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。

↑