Mining the Minoria: Unknown, Under-represented, and Under-performing Minority Groups

TL;DR

This paper introduces a geometric approach to identify hidden, under-represented, and under-performing minority groups in data without prior grouping information, addressing a critical challenge in responsible machine learning.

Contribution

It proposes a novel minority mining framework using geometric transformations and hyperplane arrangements, with solutions for both low and high-dimensional data.

Findings

Effective identification of minority groups demonstrated on real-world datasets

Proposed algorithms outperform baseline methods in detecting under-represented minorities

Theoretical analysis supports the robustness of the approach

Abstract

Due to a variety of reasons, such as privacy, data in the wild often misses the grouping information required for identifying minorities. On the other hand, it is known that machine learning models are only as good as the data they are trained on and, hence, may underperform for the under-represented minority groups. The missing grouping information presents a dilemma for responsible data scientists who find themselves in an unknown-unknown situation, where not only do they not have access to the grouping attributes but do not also know what groups to consider. This paper is an attempt to address this dilemma. Specifically, we propose a minority mining problem, where we find vectors in the attribute space that reveal potential groups that are under-represented and under-performing. Technically speaking, we propose a geometric transformation of data into a dual space and use notions such as the arrangement of hyperplanes to design an efficient algorithm for the problem in lower dimensions. Generalizing our solution to the higher dimensions is cursed by dimensionality. Therefore, we propose a solution based on smart exploration of the search space for such cases. We conduct comprehensive experiments using real-world and synthetic datasets alongside the theoretical analysis. Our experiment results demonstrate the effectiveness of our proposed solutions in mining the unknown, under-represented, and under-performing minorities.