OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport
Preprint
Abstract
Ensuring Conditional Independence (CI) constraints is pivotal for the development of fair and trustworthy machine learning models. In this paper, we introduce \sys, a framework that harnesses optimal transport theory for data repair under CI constraints. Optimal transport theory provides a rigorous framework for measuring the discrepancy between probability distributions, thereby ensuring control over data utility. We formulate the data repair problem concerning CIs as a Quadratically Constrained Linear Program (QCLP) and propose an alternating method for its solution. However, this approach faces scalability issues due to the computational cost associated with computing optimal transport distances, such as the Wasserstein distance. To overcome these scalability challenges, we reframe our problem as a regularized optimization problem, enabling us to develop an iterative algorithm inspired by Sinkhorn's matrix scaling algorithm, which efficiently addresses high-dimensional and large-scale data. Through extensive experiments, we demonstrate the efficacy and efficiency of our proposed methods, showcasing their practical utility in real-world data cleaning and preprocessing tasks. Furthermore, we provide comparisons with traditional approaches, highlighting the superiority of our techniques in terms of preserving data utility while ensuring adherence to the desired CI constraints.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Moving beyond “algorithmic bias is a data problem”Patterns, 2021
- SCODED: Statistical Constraint Oriented Data Error Detection2020
- Computing Optimal Repairs for Functional DependenciesACM Transactions on Database Systems, 2020
- Certifying and Removing Disparate Impact2015
- Bias in algorithmic filtering and personalizationEthics and Information Technology, 2013
- Unbiased look at dataset bias2011
- On approximating optimum repairs for functional dependency violations2009
- Conditional Functional Dependencies for Data Cleaning2007
- Consistent query answering in databasesACM SIGMOD Record, 2006
- Convergence of a Block Coordinate Descent Method for Nondifferentiable MinimizationJournal of Optimization Theory and Applications, 2001