Optimal Pre-Processing to Achieve Fairness and Its Relationship with Total Variation Barycenter
We use disparate impact, i.e., the extent that the probability of observing an output depends on protected attributes such as race and gender, to measure fairness. We prove that disparate impact is upper bounded by the total variation distance between the distribution of the inputs given the protected attributes. We then use pre-processing, also known as data repair, to enforce fairness. We show that utility degradation, i.e., the extent that the success of a forecasting model changes by pre-processing the data, is upper bounded by the total variation distance between the distribution of the data before and after pre-processing. Hence, the problem of finding the optimal pre-processing regiment for enforcing fairness can be cast as minimizing total variations distance between the distribution of the data before and after pre-processing subject to a constraint on the total variation distance between the distribution of the inputs given protected attributes. This problem is a linear program that can be efficiently solved. We show that this problem is intimately related to finding the barycenter (i.e., center of mass) of two distributions when distances in the probability space are measured by total variation distance. We also investigate the effect of differential privacy on fairness using the proposed the total variation distances. We demonstrate the results using numerical experimentation with a practice dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Optimal Fairness under Local Differential Privacy
We investigate how to optimally design local differential privacy (LDP) mechanisms that reduce data unfairness and thereby improve fairness in downstream classification. We first derive a closed-form optimal mechanism fo…
Reinforcement Learning with Ex-Post Max-Min Fairness
We consider reinforcement learning with vectorial rewards, where the agent receives a vector of $K\geq 2$ different types of rewards at each time step. The agent aims to maximize the minimum total reward among the $K$ re…
Fairnessreinforcement-learningReinforcement LearningReinforcement Learning (RL)A Unified Post-Processing Framework for Group Fairness in Classification
We present a post-processing algorithm for fair classification that covers group fairness criteria including statistical parity, equal opportunity, and equalized odds under a single framework, and is applicable to multic…
AttributeFairnessCan Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms
The increasing use of machine learning in learning analytics (LA) has raised significant concerns around algorithmic fairness and privacy. Synthetic data has emerged as a dual-purpose tool, enhancing privacy and improvin…
FairnessSynthetic Data GenerationAttention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing
This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concern…
FairnessProgram Repair