AI Fairness

Notes, references and materials on AI Fairness that I found useful and helped me in my research.

Reading List

• Fairness and Machine Learning: Limitations and Opportunities. Barocas, S., Hardt, M., and Narayanan, A.
• Trustworthy Machine Learning by Kush R. Varshney (Book)
• Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms
• A Framework for Benchmarking Discrimination-Aware Models in Machine Learning
• AI Fairness: How to Measure and Reduce Unwanted Bias in Machine Learning
• Fairness-aware Learning through Regularization Approach
• Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence
• Moving beyond “algorithmic bias is a data problem”
• The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
• Dissecting Racial Bias in a Credit Scoring System Experimentally Developed for the Brazilian Population
• AI Explainability 360
• AI Fairness 360
• Blog Post: A Tutorial on Fairness in Machine Learning
• CS 294: Fairness in Machine Learning
• Blog Post: Fair AI: How to Detect and Remove Bias from Financial Services AI Models
• Fairness Assessment for Artificial Intelligence in Financial Industry
• Fairlearn: A toolkit for assessing and improving fairness in AI
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• The Hidden Biases in Big Data by Kate Crawford
• Sex Bias in Graduate Admissions: Data from Berkeley
• Race After Technology: Abolitionist Tools for the New Jim Code
• Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
• Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals
• Inherent Trade-Offs in the Fair Determination of Risk Scores

COMPAS and Criminal Justice

• Machine Bias
• Code Review: FairML
• Code Review: Compas Analysis
• Fairness in Criminal Justice Risk Assessments: The State of the Art

Trade-offs and impossibility results

Classification, Calibration, Precision, Recall

• Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods
• Inherent Trade-Offs in the Fair Determination of Risk Scores
• Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
• Attacking discrimination with smarter machine learning
• Algorithmic decision making and the cost of fairness
• The problem of Infra-marginality in Outcome Tests for Discrimination
• Fairness in Streaming Submodular Maximization: Algorithms and Hardness

Inherent limitations of observational measures

• Equality of Opportunity in Supervised Learning

Beyond observational measures

Causal reasoning

• Background reading: Pearl (Chapter 1--3) , Pearl (Section 4.5.3)
• Elements of Causal Inference
• On causal interpretation of race in regressions adjusting for confounding and mediating variables

Causal fairness criteria

• Counterfactual Fairness
• Avoiding Discrimination through Causal Reasoning
• Fair Inference on Outcomes

Similarity modeling, matching

• Fairness Through Awareness
• On the (im)possibility of fairness
• Why propensity scores should not be used

Measurement, sampling

• Raw Data is an Oxymoron
• Blog Post: What's the most important thing in Statistics that's not in the textbooks
• Deconstructing Statistical Questions
• Statistics and the Theory of Measurement
• Measurement Theory and Practice: The World Through Quantification
• Survey Methodology, 2nd Edition
• Sampling: Design and Analysis

Unsupervised learning

• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

Legal and policy perspectives

• Big Data’s Disparate Impact
• It’s Not Privacy, and It’s Not Fair
• The Trouble with Algorithmic Decisions
• How Copyright Law Can Fix Artificial Intelligence's Implicit Bias Problem

Background reading

• A Theory of Justice
• Equality of Opportunity
• Causality
• Elements of Causal Inference
• Counterfactuals and Causal Inference
• Equity
• Weapons of Math Destruction

Others

References to my research, including surveys about Fairness definitions, design choices and operationalization:

• Morley, J., Kinsey, L., Elhalal, A., Garcia, F., Ziosi, M., and Floridi, L. (2023). Operationalising ai ethics: barriers, enablers and next steps. AI & SOCIETY, pages 1–13.
• Abebe, R., Hardt, M., Jin, A., Miller, J., Schmidt, L., and Wexler, R. (2022). Adversarial scrutiny of evidentiary statistical software. In 2022 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’22, page 1733–1746, New York, NY, USA. Association for Computing Machinery.
• Castelnovo, A., Crupi, R., Greco, G., Regoli, D., Penco, I. G., and Cosentini, A. C. (2022). A clarification of the nuances in the fairness metrics landscape. Scientific Reports, 12(1).
• Zhang, J., Shu, Y., and Yu, H. (2023). Fairness in design: A framework for facilitating ethical artificial intelligence designs. International Journal of Crowd Science, 7(1):32–39.
• Verma, S. and Rubin, J. (2018). Fairness definitions explained. In Proceedings of the International Workshop on Software Fairness, FairWare ’18, page 1–7, New York, NY, USA. Association for Computing Machinery.
• Tubella, A. A., Barsotti, F., Koçer, R. G., and Mendez, J. A. (2022). Ethical implications of fairness interventions: what might be hidden behind engineering choices? Ethics and Information Technology, 24(1):12
• Srivastava, M., Heidari, H., and Krause, A. (2019). Mathematical notions vs. human perception of fairness: A descriptive approach to fairness for machine learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19, page 2459–2468, New York, NY, USA. Association for Computing Machinery.
• DiCiccio, C., Hsu, B., Yu, Y., Nandy, P., and Basu, K. (2023). Detection and mitigation of algorithmic bias via predictive parity. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’23, page 1801–1816, New York, NY, USA. Association for Computing Machinery.
• Pagano, T. P., Loureiro, R. B., Lisboa, F. V. N., Peixoto, R. M., Guimarães, G. A. S., Cruz, G. O. R., Araujo, M. M., Santos, L. L., Cruz, M. A. S., Oliveira, E. L. S., Winkler, I., and Nascimento, E. G. S. (2023). Bias and unfairness in machine learning models: A systematic review on datasets, tools, fairness metrics, and identification and mitigation methods. Big Data and Cognitive Computing, 7(1).
• Chen, P., Wu, L., and Wang, L. (2023). Ai fairness in data management and analytics: A review on challenges, methodologies and applications. Applied Sciences, 13(18).
• Caton, S. and Haas, C. (2024). Fairness in machine learning: A survey. ACM Comput. Surv.,56(7).