无标签 PCA 偏差检测框架：自动找出数据中被压缩的少数群体
Identifying Representational Biases in Datasets Using PCA: A Max-Disparity Partition Framework
用 PCA 就能找出数据里被压扁的少数群体，不用组标签，结果还能直接喂给 Fair PCA 补救。
标准 PCA 最小化整体重构误差，会让少数子群体在共享投影下的保真度低于多数子群体，而 Fair PCA 等修正方法又依赖预先提供的群体标签。
该论文将问题形式化为最大差异划分（max-disparity partition），基于 Fiduccia-Mattheyses 二分框架提出贪心局部搜索算法，在完全不给组标签的前提下找出受偏差最大的数据划分。固定投影排序基线和模拟退火两个对照算法验证了该贪心解在实验中接近最优。
在 Predict Students' Dropout and Academic Success 数据集上，偏差主要由机构和专业这类社会经济地位的代理变量驱动，性别是次要但稳定的影响因素。识别出的划分可直接输入 Fair PCA，构成检测—解释—缓解的完整流程。
Identifying Representational Biases in Datasets Using PCA: A Max-Disparity Partition Framework
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 bipartitioning framework, that discovers the disparity-maximising partition without any predefined group labels. Two benchmark algorithms, a fixed-projection sorting baseline and a simulated-annealing variant, confirm that the greedy solution is empirically near-optimal. Having identified the partition, we attribute the disparity to specific features via PCA loading scores and association rule mining, enabling a practitioner to assess whether the disadvantaged group corresponds to a human-meaningful minority. On the Predict Students' Dropout and Academic Success dataset, representational disparity is driven predominantly by institutional and programmatic proxies for socioeconomic disadvantage, with gender emerging as a secondary but consistent contributor within the disadvantaged group. The discovered partition is then passed directly to Fair PCA, completing a detect-explain-mitigate pipeline.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include PCA, Fair PCA, 数据偏差, 算法公平.
Source attribution: curated from arXiv cs.LG (@Arjun KM, Shashi Jain).