Search
  • Catherine Yeo
    • Jun 25, 2020
    • 3 min read

Reading List for Fairness in AI Topics

Papers, books, and resources to learn about fairness in vision, NLP, and more

Word cloud generated by titles in this reading list



Recent discussion in the machine learning community has brought to light the importance and necessity of understanding not just machine learning, but all the considerations of bias and fairness behind every algorithm’s usage.


“This isn’t a call for ‘diversity’ in datasets or ‘improved accuracy’ in performance — it’s a call for a fundamental reconsideration of the institutions and individuals that design, develop, deploy this tech in the first place.” — Vidushi Marda

For newcomers to this field of fairness in AI, here is a compilation of helpful papers, books, and resources for learning more about the field and specific applications. This list is divided into the following categories:

  • Fairness + Computer Vision

  • Fairness + Natural Language Processing (NLP)

  • Algorithmic Fairness (Theoretical Underpinnings)

  • Books (Intended for All Audiences)

  • Survey Papers

Fairness + Computer Vision

  • Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (2018) by Joy Buolamwini and Timnit Gebru [more about the Gender Shades project here and the new documentary film Coded Bias here]

  • Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products (2019) by Inioluwa Deborah Raji and Joy Buolamwini

  • Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing (2020) by Inioluwa Deborah Raji et al.

  • Predictive Inequity in Object Detection (2019) by Benjamin Wilson, Judy Hoffman, and Jamie Morgenstern

  • Deep Learning for Face Recognition: Pride or Prejudiced? (2019) by Shruti Nagpal et al.

  • No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World (2017) by Shreya Shankar et al.

  • ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases (2017) by Pierre Stock and Moustapha Cisse

  • Tutorial (2020): Fairness, Accountability, Transparency, and Ethics in Computer Vision by Timnit Gebru and Emily Denton

Fairness + NLP

  • The Social Impact of Natural Language Processing (2016) by Dirk Hovy and Shannon L. Spruit

  • Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016) by Tolga Bolukbasi et al.

  • Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints (2017) by Jieyu Zhao et al.

  • Women Also Snowboard: Overcoming Bias in Captioning Models (2018) by Kaylee Burns et al.

  • Mitigating unwanted biases with adversarial learning (2018) by Brian Hu Zhang, Blake Lemoine, Margaret Mitchell

  • Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them (2019) by Hila Gonen and Yoav Goldberg

  • Principled Frameworks for Evaluating Ethics in NLP Systems (2019) by Shrimai Prabhumoye, Elijah Mayfield, and Alan W. Black

  • Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting (2019) by Maria De-Arteaga et al.

  • Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020) by Su Lin Blodgett et al.

  • Tutorial (2019): Bias and Fairness in Natural Language Processing by Kai-Wei Chang, Vicente Ordonez, Margaret Mitchell, and Vinodkumar Prabhakaran

Books (Intended for All Audiences)

  • Weapons of Math Destruction by Cathy O’Neil

  • The Ethical Algorithm by Michael Kearns and Aaron Roth

  • Algorithms of Oppression by Safiya Umoja Noble

  • Automating Inequality by Virginia Eubanks

  • Artificial Unintelligence: How Computers Misunderstand the World by Meredith Broussard

  • Fairness and Machine Learning textbook by Solon Barocas, Moritz Hardt, and Arvind Narayanan (work in progress)

Survey Papers

  • The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning (2018) by Sam Corbett-Davies and Sharad Goel

  • The Frontiers of Fairness in Machine Learning (2018) by Alexandra Chouldechova and Aaron Roth

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

  • Fairness in Deep Learning: A Computational Perspective (2020) by Megnan Du et al.


I plan to continue updating this list over time. If you have any suggestions for papers, books, areas, and resources to add to this list, comment below or let me know on Twitter.


. . .