AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias

Abstract

Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.

The What-If Tool: Interactive Probing of Machine Learning Models

“…A key feature of WIT is that it can calculate ML fairness metrics on trained models. Many current tools offer a similar capability: IBM AI Fairness 360 [7], Audit AI [26], and GAMut [14]. A distinguishing element of our tool is its ability to interactively apply optimization procedures to make posttraining classification threshold adjustments to improve those metrics.…”

Fair Adversarial Gradient Tree Boosting

“…Algorithms which belong to the "pre-processing" family ensure that the input data is fair. This can be achieved by suppressing the sensitive attributes, by changing class labels of the data set, and by reweighting or resampling the data [11,12,13].…”

Dataset bias: A case study for visual question answering

“…Ethical issues in machine learning are being studied by researchers in both academia (X. Jiang, Sun, Yang, Zhuge, & Yao, ; Katell, ; Lepri, Oliver, Letouzé, Pentland, & Vinck, ; Nikolov, Lalmas, Flammini, & Menczer, ; Wilkie & Azzopardi, ) and industry , (Bellamy et al, ). The ubiquity of machine learning applications is a reason for the increasing concern.…”