FairLRF: Achieving Fairness through Sparse Low Rank Factorization Article Swipe

MAKE IMPACT

Guo Yuanbo , Xia Jun , Shi, Yiyu · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.16549

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.

Type

preprint

Landing Page

https://doi.org/10.48550/arxiv.2511.16549

OA Status

green

OpenAlex ID

https://openalex.org/W7106327613

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7106327613

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2511.16549

Digital Object Identifier

Title

FairLRF: Achieving Fairness through Sparse Low Rank Factorization

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-20

Full publication date if available

Authors

Guo Yuanbo, Xia Jun, Shi, Yiyu

List of authors in order

Landing page

https://doi.org/10.48550/arxiv.2511.16549

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://doi.org/10.48550/arxiv.2511.16549

Direct OA link when available

Concepts

Singular value decomposition, Debiasing, Computer science, Matrix decomposition, Factorization, Variety (cybernetics), Unitary state, Rank (graph theory), Low-rank approximation, Algorithm, Compression (physics), Decomposition, Sparse matrix, Value (mathematics), Theoretical computer science, Unitary transformation, Singular value, Field (mathematics), Performance improvement, Group (periodic table), Mathematical optimization, Artificial intelligence, Work (physics), Compression ratio, Data compression, Unitary matrix, Learning to rank, Base (topology)

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload