OxEnsemble: Fair Ensembles for Low-Data Classification

Jonathan Rystrøm, Zihao Fu, Chris Russell

Keywords: Algorithmic fairness, Group fairness, Minimum recall, Equal opportunity, Ensemble learning, Low-data learning, Theoretical guarantees

TL;DR: We introduce a novel method using fair deep ensembles that work well with extremely low-data groups with theoretical guarantees.

Abstract:

We address the problem of fair classification in settings where data is scarce and unbalanced across demographic groups. Such low-data regimes are common in domains like medical imaging, where false negatives can have fatal consequences.

We propose a novel approach _OxEnsemble_ for efficiently training ensembles and enforcing fairness in these low-data regimes. Unlike other approaches, we aggregate predictions across ensemble members, each trained to satisfy fairness constraints. By construction, _OxEnsemble_ is both data-efficient, carefully reusing held-out data to enforce fairness reliably, and compute-efficient, requiring little more compute than used to fine-tune or evaluate an existing model. We validate this approach with new theoretical guarantees.
Experimentally, our approach yields more consistent outcomes and stronger fairness-accuracy trade-offs than existing methods across multiple challenging medical imaging classification datasets.

Primary Subject Area: Fairness and Bias

Secondary Subject Area: Learning with Noisy Labels and Limited Data

Registration Requirement: Yes

Reproducibility: https://github.com/jhrystrom/guaranteed-fair-ensemble

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 27