FairLRF: Achieving Fairness through Sparse Low Rank Factorization

TL;DR

FairLRF introduces a novel approach using singular value decomposition to selectively remove bias-inducing components from model weights, significantly improving fairness in deep learning models without substantial accuracy loss.

Contribution

This work is the first to leverage SVD for fairness enhancement by removing bias-related elements from unitary matrices, offering an efficient alternative to existing methods.

Findings

Outperforms existing fairness methods in experiments

Effectively reduces group disparities in model predictions

Hyper-parameter tuning influences fairness outcomes

Abstract

As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly in sensitive fields such as medical diagnosis. Although a variety of bias-mitigation methods have been proposed, many rely on computationally expensive debiasing strategies or suffer substantial drops in model accuracy, which limits their practicality in real-world, resource-constrained settings. To address this issue, we propose a fairness-oriented low rank factorization (LRF) framework that leverages singular value decomposition (SVD) to improve DL model fairness. Unlike traditional SVD, which is mainly used for model compression by decomposing and reducing weight matrices, our work shows that SVD can also serve as an effective tool for fairness enhancement. Specifically, we observed that elements in the unitary matrices obtained from SVD contribute unequally to model bias across groups defined by sensitive attributes. Motivated by this observation, we propose a method, named FairLRF, that selectively removes bias-inducing elements from unitary matrices to reduce group disparities, thus enhancing model fairness. Extensive experiments show that our method outperforms conventional LRF methods as well as state-of-the-art fairness-enhancing techniques. Additionally, an ablation study examines how major hyper-parameters may influence the performance of processed models. To the best of our knowledge, this is the first work utilizing SVD not primarily for compression but for fairness enhancement.