ABSTRACT
Calls to action to implement evaluation of fairness and bias into industry systems are increasing at a rapid rate. The research community has attempted to meet these demands by producing ethical principles and guidelines for AI, but few of these documents provide guidance on how to implement these principles in real world settings. Without readily available standardized and practice-tested approaches for evaluating fairness in recommendation systems, industry practitioners, who are often not experts, may easily run into challenges or implement metrics that are potentially poorly suited to their specific applications. When evaluating recommendations, practitioners are well aware they should evaluate their systems for unintended algorithmic harms, but the most important, and unanswered question, is how? In this talk, we will present practical challenges we encountered in addressing algorithmic responsibility in recommendation systems, which also present research opportunities for the RecSys community. This talk will focus on the steps that need to happen before bias mitigation can even begin.
Supplemental Material
- Chloé Bakalar, Renata Barreto, Stevie Bergman, Miranda Bogen, Bobbie Chern, Sam Corbett-Davies, Melissa Hall, Isabel Kloumann, Michelle Lam, Joaquin Quiñonero Candela, 2021. Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems. arXiv preprint abs/2103.06172 (2021).Google Scholar
- Solon Barocas, Kate Crawford, Aaron Shapiro, and Hanna Wallach. 2017. The problem with bias: Allocative versus representational harms in machine learning.Google Scholar
- Sarah Bird, Miro Dudík, Richard Edgar, Brandon Horn, Roman Lutz, Vanessa Milan, Mehrnoosh Sameki, Hanna Wallach, and Kathleen Walker. 2020. Fairlearn: A toolkit for assessing and improving fairness in AI. Technical Report MSR-TR-2020-32. Microsoft.Google Scholar
- Avriel Epps-Darling, Romain Takeo Bouyer, and Henriette Cramer. 2020. Artist gender representation in music streaming. In Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR 2020). ISMIR. ISMIR, Montréal, Canada, 248–254.Google Scholar
- European Parliament. Directorate General for Parliamentary Research Services.2019. A governance framework for algorithmic accountability and transparency.Publications Office, LU. https://data.europa.eu/doi/10.2861/59990Google Scholar
- Sahin Cem Geyik, Stuart Ambler, and Krishnaram Kenthapadi. 2019. Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Anchorage, AK, USA) (KDD ’19). Association for Computing Machinery, New York, NY, USA, 2221–2231. https://doi.org/10.1145/3292500.3330691Google ScholarDigital Library
- Abigail Z. Jacobs and Hanna Wallach. 2021. Measurement and Fairness. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (Virtual Event, Canada) (FAccT ’21). Association for Computing Machinery, New York, NY, USA, 375–385. https://doi.org/10.1145/3442188.3445901Google ScholarDigital Library
- Anna Jobin, Marcello Ienca, and Effy Vayena. 2019. The global landscape of AI ethics guidelines. Nature Machine Intelligence 1, 9 (2019), 389–399.Google ScholarCross Ref
- Michelle Seng Ah Lee and Jat Singh. 2021. The Landscape and Gaps in Open Source Fairness Toolkits. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 699, 13 pages. https://doi.org/10.1145/3411764.3445261Google ScholarDigital Library
- Arvind Narayanan. 2018. Translation tutorial: 21 fairness definitions and their politics.Google Scholar
- U.S. Department of Labor. 2021. Practical Significance in EEO Analysis Frequently Asked Questions | U.S. Department of Labor. https://www.dol.gov/agencies/ofccp/faqs/practical-significanceGoogle Scholar
- Inioluwa Deborah Raji, Andrew Smart, Rebecca N. White, Margaret Mitchell, Timnit Gebru, Ben Hutchinson, Jamila Smith-Loud, Daniel Theron, and Parker Barnes. 2020. Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (Barcelona, Spain) (FAT* ’20). Association for Computing Machinery, New York, NY, USA, 33–44. https://doi.org/10.1145/3351095.3372873Google ScholarDigital Library
- Brianna Richardson, Jean Garcia-Gathright, Samuel F. Way, Jennifer Thom, and Henriette Cramer. 2021. Towards Fairness in Practice: A Practitioner-Oriented Rubric for Evaluating Fair ML Toolkits. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 236, 13 pages. https://doi.org/10.1145/3411764.3445604Google ScholarDigital Library
- Elizabeth Anne Watkins, Michael McKenna, and Jiahao Chen. 2022. The Four-Fifths Rule is Not Disparate Impact: A Woeful Tale of Epistemic Trespassing in Algorithmic Fairness. arXiv preprint arXiv:2202.09519 (2022).Google Scholar
Index Terms
- Challenges in Translating Research to Practice for Evaluating Fairness and Bias in Recommendation Systems
Recommendations
Scoping Fairness Objectives and Identifying Fairness Metrics for Recommender Systems: The Practitioners’ Perspective
WWW '23: Proceedings of the ACM Web Conference 2023Measuring and assessing the impact and “fairness’’ of recommendation algorithms is central to responsible recommendation efforts. However, the complexity of fairness definitions and the proliferation of fairness metrics in research literature have led ...
User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms
RecSys '21: Proceedings of the 15th ACM Conference on Recommender SystemsThere are various biases in recommender systems. Recognizing biases, as well as unfairness caused by problematic biases, is the first step of system optimization. Related studies on algorithmic biases are mainly from the perspective of either items or ...
The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation
RecSys '20: Proceedings of the 14th ACM Conference on Recommender SystemsRecently there has been a growing interest in fairness-aware recommender systems including fairness in providing consistent performance across different users or groups of users. A recommender system could be considered unfair if the recommendations do ...
Comments