5. Further Resources

There are many resources to help you learn more about fairness in machine learning. Below we list some of the materials that we have found helpful, while acknowledging that the list is vastly incomplete.

5.1. Books

• Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy (O’Neill, 2016)

• Artificial Unintelligence: How Computers Misunderstand the World (Broussard, 2018)

• Algorithms of Oppression: How Search Engines Reinforce Racism (Noble, 2018)

• Fairness and Machine Learning (Barocas, Hardt, & Narayanan)

5.2. Papers

• Fairlearn: A toolkit for assessing and improving fairness in AI (Bird et al., 2020)

• Fairness through Awareness (Dwork et al., 2011)

• Big Data’s Disparate Impact (Barocas & Selbst, 2016)

• Measures and Mismeasures of Fairness (Corbett-Davies & Goel, 2018)

• Fairness and Abstraction in Sociotechnical Systems (Selbst et al., 2018)

• A Survey on Bias and Fairness in Machine Learning (Mehrabi et al., 2019)

• Algorithmic Fairness from a Non-ideal Perspective (Fazelpour & Lipton, 2020)

• Co-Designing Checklists to Understand Organizational Challenges and Opportunities around Fairness in AI (Madaio et al., 2020)

5.3. Online demos, talks, tutorials

• Fairness in Machine Learning (NeurIPS 2017 Tutorial)

• Gender Shades Project