SOURCE-LINKED INTELLIGENCE

Identifying Representational Biases in Datasets Using PCA: A Max-Disparity Partition Framework

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Principal Component Analysis (PCA) minimises aggregate reconstruction error, which can inadvertently represent majority subgroups with substantially higher fidelity than minority subgroups. Fairness-aware extensions of PCA correct this disparity but require group labels as input. We address the logically prior question: given only a data matrix, which binary partition of the data suffers the greatest representational disparity under a shared PCA projection? We formalise this as the max-disparity partition problem and propose a greedy local-search algorithm, grounded in the Fiduccia-Mattheyses

Read original source ↗ Open in workspace

recordType

paper

region

Global