A method for generating natural fairness test cases for machine learning models
By constructing agent decision boundaries in the latent space and designing latent vector candidate detection strategies, fair test cases that conform to natural laws are generated, solving the problem that test cases in existing technologies do not conform to natural laws and improving the fairness and credibility of machine learning models.
CN116662153BActive Publication Date: 2026-05-26BEIHANG UNIV
View PDF 1 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIHANG UNIV
- Filing Date
- 2023-04-17
- Publication Date
- 2026-05-26
Smart Images
Figure CN116662153B_ABST
Abstract
This invention discloses a method for generating natural fairness test cases for machine learning models. It simulates the decision-making process of a machine learning model in the latent space by constructing a dataset, deriving an approximate proxy decision boundary. Furthermore, leveraging the model's inrocity at the decision boundary, a latent vector candidate detection strategy is designed to generate fairness test cases that conform to natural laws near the proxy decision boundary. This helps to better test the fairness characteristics of machine learning models in real-world scenarios and improves the fairness and credibility of machine learning models. This invention can be applied to generating natural fairness test cases for structured data such as tables and unstructured data such as images, demonstrating good application value and practical effectiveness.
Need to check novelty before this filing date? Find Prior Art