Themis: automatically testing software for discrimination

By Rico Angell, Brittany Johnson, Yuriy Brun, Alexandra Meliou. 2018

89 citations recorded by the source corpus.

Bias in decisions made by modern software is becoming a common and serious problem. We present Themis, an automated test suite generator to measure two types of discrimination, including causal relationships between sensitive inputs and program behavior. We explain how Themis can measure discrimination and aid its debugging, describe a set of optimizations Themis uses to reduce test suite size, and demonstrate Themis' effectiveness on open-source software. Themis is open-source and all our evaluation data are available at http://fairness.cs.umass.edu/. See a video of Themis in action: https://youtu.be/brB8wkaUesY

Subfields: Information Systems, Software

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Jie M. Zhang
2. Yang Liu
3. Lei Ma
4. Shira Mitchell
5. Mark Harman
6. Solon Barocas
7. Kristian Lum
8. Eric Potash

In Software

1. Jie M. Zhang
2. Yang Liu
3. Lei Ma
4. Mark Harman
5. Phil McMinn
6. Yue Jia
7. Claire Le Goues
8. Koushik Sen

Citations in the corpus

• Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “Fairness in ML has been explored in popular books [98, 34] and a White House report [35], surveyed in technical review papers [8, 40, 15, 126], and an in-progress textbook [5], and inspired a number of software packages [132, 38, 2, 43, 47].”
• Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need? (2018, neutral): “As the field matures, integrated toolkits are being developed, with the aim of making these methods more widely accessible and usable [7, 28, 35, 42, 70].”
• Machine Learning Testing: Survey, Landscapes and Horizons (2019, methodology): “[5], [213] proposed Themis which considers group fairness using causal analysis [214].”
• Algorithmic Fairness: Choices, Assumptions, and Definitions (2021, background): “…in technical review articles (Berk et al. 2017, Chouldechova & Roth 2018, Friedler et al. 2018, Verma & Rubin 2018) and an in-progress textbook (Barocas et al. 2018), and has inspired a number of software packages (Galhotra et al. 2017, Zehlike et al. 2017, Angell et al. 2018, Wexler 2018).”