Summary of Towards Fairness and Privacy: a Novel Data Pre-processing Optimization Framework For Non-binary Protected Attributes, by Manh Khoi Duong and Stefan Conrad
Towards Fairness and Privacy: A Novel Data Pre-processing Optimization Framework for Non-binary Protected Attributes
by Manh Khoi Duong, Stefan Conrad
First submitted to arxiv on: 1 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed framework addresses unfair outcomes in AI by debiasing datasets containing a protected attribute. The combinatorial optimization problem utilizes heuristics like genetic algorithms to achieve fairness objectives. The framework finds a data subset that minimizes discrimination measures, enabling use cases such as data removal or synthetic data addition. In particular, exclusive synthetic data use preserves privacy while optimizing for fairness. Comprehensive evaluation shows genetic algorithms effectively produce fairer datasets compared to originals. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI can be unfair due to biased datasets. This paper helps by debiasing these datasets with a protected attribute. It uses an optimization problem and heuristics like genetic algorithms to achieve fairness. The goal is to find the best subset of data that minimizes discrimination. You can use this method to remove data, add synthetic data, or only use synthetic data. This approach preserves privacy while making things fairer. |
Keywords
» Artificial intelligence » Optimization » Synthetic data
