Achieving Fair PCA Using Joint Eigenvalue Decomposition
This addresses fairness issues in dimensionality reduction for applications involving demographic data, though it appears incremental as it builds on existing PCA and JEVD techniques.
The paper tackles the problem of PCA producing biased representations against demographic groups by proposing a fair PCA method using Joint Eigenvalue Decomposition (JEVD), which outperforms baselines in fairness and quality on various datasets.
Principal Component Analysis (PCA) is a widely used method for dimensionality reduction, but it often overlooks fairness, especially when working with data that includes demographic characteristics. This can lead to biased representations that disproportionately affect certain groups. To address this issue, our approach incorporates Joint Eigenvalue Decomposition (JEVD), a technique that enables the simultaneous diagonalization of multiple matrices, ensuring fair and efficient representations. We formally show that the optimal solution of JEVD leads to a fair PCA solution. By integrating JEVD with PCA, we strike an optimal balance between preserving data structure and promoting fairness across diverse groups. We demonstrate that our method outperforms existing baseline approaches in fairness and representational quality on various datasets. It retains the core advantages of PCA while ensuring that sensitive demographic attributes do not create disparities in the reduced representation.