· 2013
Learning Fair Representations
- 1,002citations
- 2013year
Short summary
A new algorithm learns data representations that simultaneously satisfy group and individual fairness criteria by optimizing for data encoding and protected group information obfuscation.
AI-generated from the title and abstract; the full text is not read.
Key points
- Proposes a learning algorithm for classification that achieves both group and individual fairness.
- Formulates fairness as an optimization problem balancing data encoding and protected group information obfuscation.
- Demonstrates positive results on three datasets compared to known techniques.
- The learned intermediate representation supports transfer learning for other classification tasks.
- The approach contributes to learning a distance metric for identifying important classification dimensions.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source., 2013 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Safety Research
Safety ResearchSocial Sciences