Learning Fair Representations
Rich Zemel, Yu Wu, Kevin Swersky et al. · 2013
We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly). We formulate fairness as an optimization problem of finding a good representation of the data with two competing goals: to encode the data as well as possible, while simultaneously obfuscating any information about membership in the protected group. We show positive results of our algorithm relative to other known techniques, on three datasets. Moreover, we demonstrate several advantages to our approach. First, our intermediate representation can be used for other classification tasks (i.e., transfer learning is possible); secondly, we take a step toward learning a distance metric which can find important dimensions of the data for classification. 1.
Cited by 898 works.
Authors
References
- UCI Machine Learning Repository
- Calibrating Noise to Sensitivity in Private Data Analysis
- Fairness through awareness
- The information bottleneck method
- Scaling up the accuracy of Naive-Bayes classifiers: a decision-tree hybrid
- Three naive Bayes approaches for discrimination-free classification
- Discrimination-aware data mining
- Classifying without discriminating
- Fairness-aware Learning through Regularization Approach
- k-NN as an implementation of situation testing for discrimination discovery and prevention