Sarah Bird
Krishnaram Kenthapadi
ABSTRACT
Researchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population groups, due to biases in algorithmic decision-making systems. This tutorial aims to present an overview of algorithmic bias / discrimination issues observed over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving fairness in machine learning systems. We will motivate the need for adopting a “fairness-first” approach (as opposed to viewing algorithmic bias / fairness considerations as an afterthought), when developing machine learning based models and systems for different consumer and enterprise applications. Then, we will focus on the application of fairness-aware machine learning techniques in practice, by highlighting industry best practices and case studies from different technology companies. Based on our experiences in industry, we will identify open problems and research challenges for the data mining / machine learning community.
- J. Angwin, J. Larson, S. Mattu, and L. Kirchner. Machine bias. ProPublica, 2016.Google Scholar
- S. Barocas and M. Hardt. Fairness in machine learning. In NIPS Tutorial, 2017.Google Scholar
- A. Caliskan, J. J. Bryson, and A. Narayanan. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334), 2017.Google Scholar
- L. E. Celis, D. Straszak, and N. K. Vishnoi. Ranking with fairness constraints. In ICALP, 2018.Google Scholar
- S. Corbett-Davies, E. Pierson, A. Feller, S. Goel, and A. Huq. Algorithmic decision making and the cost of fairness. In KDD, 2017. Google ScholarDigital Library
- C. Dwork, M. Hardt, T. Pitassi, and R. Z. Omer Reingold. Fairness through awareness. In ITCS, 2012. Google ScholarDigital Library
- S. A. Friedler, C. Scheidegger, and S. Venkatasubramanian. On the (im) possibility of fairness. arXiv:1609.07236, 2016.Google Scholar
- S. A. Friedler, C. Scheidegger, S. Venkatasubramanian, S. Choudhary, E. P. Hamilton, and D. Roth. A comparative study of fairness-enhancing interventions in machine learning. arXiv:1802.04422, 2018.Google Scholar
- B. Friedman and H. Nissenbaum. Bias in computer systems. ACM Transactions on Information Systems (TOIS), 14(3), 1996. Google ScholarDigital Library
- S. C. Geyik and K. Kenthapadi. Building representative talent search at LinkedIn. LinkedIn engineering blog post, Available at https://engineering.linkedin.com/blog/2018/10/building-representative-talent-search-at-linkedin, October 2018.Google Scholar
- S. Hajian, F. Bonchi, and C. Castillo. Algorithmic bias: From discrimination discovery to fairness-aware data mining. In KDD Tutorial on Algorithmic Bias, 2016. Google ScholarDigital Library
- S. Hajian, J. Domingo-Ferrer, and O. Farràs. Generalization-based privacy preservation and discrimination prevention in data publishing and mining. Data Mining and Knowledge Discovery, 28(5-6), 2014. Google ScholarDigital Library
- M. Hardt, E. Price, and N. Srebro. Equality of opportunity in supervised learning. In NIPS, 2016. Google ScholarDigital Library
- S. Jabbari, M. Joseph, M. Kearns, J. Morgenstern, and A. Roth. Fairness in reinforcement learning. In ICML, 2017. Google ScholarDigital Library
- J. Kleinberg, S. Mullainathan, and M. Raghavan. Inherent trade-offs in the fair determination of risk scores. In ITCS, 2017.Google Scholar
- D. Pedreschi, S. Ruggieri, and F. Turini. Discrimination-aware data mining. In KDD, 2008. Google ScholarDigital Library
- B. Woodworth, S. Gunasekar, M. I. Ohannessian, and N. Srebro. Learning non-discriminatory predictors. In COLT, 2017.Google Scholar
- M. B. Zafar, I. Valera, M. Gomez Rodriguez, and K. P. Gummadi. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In WWW, 2017. Google ScholarDigital Library
- M. Zehlike, F. Bonchi, C. Castillo, S. Hajian, M. Megahed, and R. Baeza-Yates. FA*IR: A fair top-k ranking algorithm. In CIKM, 2017. Google ScholarDigital Library
- R. Zemel, Y. Wu, K. Swersky, T. Pitassi, and C. Dwork. Learning fair representations. In ICML, 2013. Google ScholarDigital Library
Recommendations
Fairness-Aware Machine Learning: Practical Challenges and Lessons Learned
WSDM '19: Proceedings of the Twelfth ACM International Conference on Web Search and Data MiningResearchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population ...
A Survey on Bias and Fairness in Machine Learning
Invited TutorialWith the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive ...
A Review on Fairness in Machine Learning
An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence and machine learning (ML) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, ...
Reviews
Jonathan P. E. Hodgson
This is a timely paper in light of recent stories about bias in artificial intelligence (AI) systems, such as the COMPAS system used in Florida to predict recidivism. The tutorial's aim is to describe what the authors call a "fairness-first approach" to machine learning. This is similar to a security-first view of system construction, that is, fairness should be built in from the start rather than bolted on later. The tutorial covers industry best practices, sources of bias, algorithmic techniques for fairness, and fairness methods in practice. The notion of fairness is discussed along with various definitions, for example, individual and group fairness. This includes fairness in ranking users for things like credit offers. A bibliography provides further references on this important topic. For those who missed the conference tutorial, and because this paper is just a brief invitation to it, readers should refer to the papers listed in the bibliography for more comprehensive introductions to the topic of fairness in machine learning.
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments