Themis-ml: A Fairness-Aware Machine Learning Interface for End-To-End Discrimination Discovery and Mitigation

By Niels Bantilan. 2017

83 citations recorded by the source corpus.

ABSTRACT As more industries integrate machine learning into socially sensitive decision processes like hiring, loan-approval, and parole-granting, we are at risk of perpetuating historical and contemporary socioeconomic disparities. This is a critical problem because on the one hand, organizations who use but do not understand the discriminatory potential of such systems will facilitate the widening of social disparities under the assumption that algorithms are categorically objective. On the other hand, the responsible use of machine learning can help us measure, understand, and mitigate the implicit historical biases in socially sensitive data by expressing implicit decision-making mental models in terms of explicit statistical models. In this article we specify, implement, and evaluate a “fairness-aware” machine learning interface called themis-ml, which is intended for use by individual data scientists and engineers, academic research teams, or larger product teams who use machine learning in production systems.

Subfields: Safety Research

How researchers see this paper

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

In Safety Research

Citations in the corpus

FairSight: Visual Analytics for Fairness in Decision Making (2019, methodology): “With the increasing awareness of the importance of fair machine learning, a number of new tools, including API [3] and interface [40], as well as integrated systems such as the What-if tool [15] or AI Fairness 360 [22], have been developed.”
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias (2018, background): “Themis-ML (Bantilan, 2018) is one such repository that provides a few fairness metrics, such as mean difference, as well as some bias mitigation algorithms, such as relabeling (Kamiran & Calders, 2012), additive counterfactually fair estimator (Kusner et al., 2017), and reject option classiﬁcation…”
Mitigation of Unintended Biases against Non-Native English Texts in Sentiment Analysis (2019, background): “When this preference is not intentional, the fairness of the model needs to be questioned [1].”
Is there Gender bias and stereotype in Portuguese Word Embeddings? (2018, background): “In [1] the authors propose to specify, implement, and evaluate the “fairness-aware” ML interface called themis-ml.”
Ethical Considerations in AI-Based Recruitment (2019, methodology): “ Themis-ML [36]: Like AIF360, Themis-ML provides tools for all three classes of fairness algorithms, by providing pre-processing methods, pre-built classification models that meet fairness criteria, and post-processing awareness estimators.”