A Causal Framework for Discovering and Removing Direct and Indirect Discrimination
Document Type
Conference Proceeding
Publication Date
2017
Keywords
AI, Security, Privacy, Social sciences
Abstract
In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e.g., building classifiers). The main drawback of existing methods is that they cannot distinguish the part of influence that is really caused by discrimination from all correlated influences. In our approach, we make use of the causal network to capture the causal structure of the data. Then we model direct and indirect discrimination as the path-specific effects, which accurately identify the two types of discrimination as the causal effects transmitted along different paths in the network. Based on that, we propose an effective algorithm for discovering direct and indirect discrimination, as well as an algorithm for precisely removing both types of discrimination while retaining good data utility. Experiments using the real dataset show the effectiveness of our approaches.
Citation
Zhang, L., Wu, Y., & Wu, X. (2017). (2017). A causal framework for discovering and removing direct and indirect discrimination. Paper presented at the Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, {IJCAI-17}, 3. doi: https://doi.org/10.24963/ijcai.2017/549
Comments
Principal Investigator: Xintao Wu