Topic modeling, or more broadly, dimensionality reduction, techniques provide powerful tools for uncovering patterns in large datasets and are widely applied across various domains. We investigate how Non-negative Matrix Factorization (NMF) can introduce bias in the representation of data groups, such as those defined by demographics or protected attributes. We present an approach, called Fairer-NMF, that seeks to minimize the maximum reconstruction loss for different groups relative to their size and intrinsic complexity. Further, we present two algorithms for solving this problem. The first is an alternating minimization (AM) scheme and the second is a multiplicative updates (MU) scheme which demonstrates a reduced computational time compared to AM while still achieving similar performance. Lastly, we present numerical experiments on synthetic and real datasets to evaluate the overall performance and trade-offs of Fairer-NMF
翻译:主题建模,或更广义的降维技术,为揭示大型数据集中的模式提供了强大工具,并广泛应用于各个领域。我们研究了非负矩阵分解(NMF)如何在数据组的表示中引入偏差,这些数据组可由人口统计学特征或受保护属性定义。我们提出了一种称为Fairer-NMF的方法,旨在最小化不同组相对于其规模和内在复杂性的最大重构损失。此外,我们提出了两种解决此问题的算法。第一种是交替最小化(AM)方案,第二种是乘法更新(MU)方案,该方案在保持相似性能的同时,相比AM展示了更短的计算时间。最后,我们在合成和真实数据集上进行了数值实验,以评估Fairer-NMF的整体性能与权衡。