FairLRF: Achieving Fairness through Sparse Low Rank Factorization
By: Yuanbo Guo, Jun Xia, Yiyu Shi
Potential Business Impact:
Makes AI fairer without losing accuracy.
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.
Similar Papers
Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing
Machine Learning (CS)
Makes big computer brains smaller and faster.
FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA
Computers and Society
Makes AI treat all patients fairly in hospitals.
Post-processing for Fair Regression via Explainable SVD
Machine Learning (CS)
Makes computer predictions fair for everyone.