Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems

• URL: http://arxiv.org/abs/2103.06172v1
• Date: Wed, 10 Mar 2021 16:42:20 GMT
• Title: Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems
• Authors: Chlo\'e Bakalar, Renata Barreto, Miranda Bogen, Sam Corbett-Davies, Melissa Hall, Isabel Kloumann, Michelle Lam, Joaquin Qui\~nonero Candela, Manish Raghavan, Joshua Simons, Jonathan Tannen, Edmund Tong, Kate Vredenburgh, Jiejing Zhao
• Abstract summary: This paper presents an example of applying algorithmic fairness approaches to complex production systems within the context of a large technology company. We discuss how we disentangle normative questions of product and policy design from empirical questions of system implementation. We also present an approach for answering questions of the latter sort, which allows us to measure how machine learning systems and human labelers are making these tradeoffs.
• Score: 4.288137349392433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world systems. This paper presents an example of one team's approach to the challenge of applying algorithmic fairness approaches to complex production systems within the context of a large technology company. We discuss how we disentangle normative questions of product and policy design (like, "how should the system trade off between different stakeholders' interests and needs?") from empirical questions of system implementation (like, "is the system achieving the desired tradeoff in practice?"). We also present an approach for answering questions of the latter sort, which allows us to measure how machine learning systems and human labelers are making these tradeoffs across different relevant groups. We hope our experience integrating fairness tools and approaches into large-scale and complex production systems will be useful to other practitioners facing similar challenges, and illuminating to academics and researchers looking to better address the needs of practitioners.

Related papers

• Application-Driven Innovation in Machine Learning [56.85396167616353]
  We describe the paradigm of application-driven research in machine learning. We show how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation.
  arXiv  Detail & Related papers  (2024-03-26T04:59:27Z)
• FairCompass: Operationalising Fairness in Machine Learning [34.964477625987136]
  There is a growing imperative to develop responsible AI solutions. Despite a diverse assortment of machine learning fairness solutions is proposed in the literature. There is reportedly a lack of practical implementation of these tools in real-world applications.
  arXiv  Detail & Related papers  (2023-12-27T21:29:53Z)
• Embedding in Recommender Systems: A Survey [67.67966158305603]
  A crucial aspect is embedding techniques that covert the high-dimensional discrete features, such as user and item IDs, into low-dimensional continuous vectors. Applying embedding techniques captures complex entity relationships and has spurred substantial research. This survey covers embedding methods like collaborative filtering, self-supervised learning, and graph-based techniques.
  arXiv  Detail & Related papers  (2023-10-28T06:31:06Z)
• Machine Unlearning: A Survey [56.79152190680552]
  A special need has arisen where, due to privacy, usability, and/or the right to be forgotten, information about some specific samples needs to be removed from a model, called machine unlearning. This emerging technology has drawn significant interest from both academics and industry due to its innovation and practicality. No study has analyzed this complex topic or compared the feasibility of existing unlearning solutions in different kinds of scenarios. The survey concludes by highlighting some of the outstanding issues with unlearning techniques, along with some feasible directions for new research opportunities.
  arXiv  Detail & Related papers  (2023-06-06T10:18:36Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Fairness in Recommender Systems: Research Landscape and Future Directions [119.67643184567623]
  We review the concepts and notions of fairness that were put forward in the area in the recent past. We present an overview of how research in this field is currently operationalized. Overall, our analysis of recent works points to certain research gaps.
  arXiv  Detail & Related papers  (2022-05-23T08:34:25Z)
• A Framework for Fairness: A Systematic Review of Existing Fair AI Solutions [4.594159253008448]
  A large portion of fairness research has gone to producing tools that machine learning practitioners can use to audit for bias while designing their algorithms. There is a lack of application of these fairness solutions in practice. This review provides an in-depth summary of the algorithmic bias issues that have been defined and the fairness solution space that has been proposed.
  arXiv  Detail & Related papers  (2021-12-10T17:51:20Z)
• An Overview of Recommender Systems and Machine Learning in Feature Modeling and Configuration [55.67505546330206]
  We give an overview of a potential new line of research which is related to the application of recommender systems and machine learning techniques. In this paper, we give examples of the application of recommender systems and machine learning and discuss future research issues.
  arXiv  Detail & Related papers  (2021-02-12T17:21:36Z)
• Specialization in Hierarchical Learning Systems [0.0]
  We investigate in how far information constraints in hierarchies of experts not only provide a principled method for regularization but also to enforce specialization. We devise an information-theoretically motivated on-line learning rule that allows partitioning of the problem space into multiple sub-problems that can be solved by the individual experts. We show the broad applicability of our approach on a range of problems including classification, regression, density estimation, and reinforcement learning problems.
  arXiv  Detail & Related papers  (2020-11-03T17:00:31Z)
• Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness [6.6358581196331095]
  We argue that building fair decision-making systems requires overcoming limitations inherent to each field. We begin to lay the ground work towards this goal by comparing the perspective each discipline takes on fair decision-making.
  arXiv  Detail & Related papers  (2020-10-12T03:42:20Z)
• A systematic review and taxonomy of explanations in decision support and recommender systems [13.224071661974596]
  We systematically review the literature on explanations in advice-giving systems. We derive a novel comprehensive taxonomy of aspects to be considered when designing explanation facilities.
  arXiv  Detail & Related papers  (2020-06-15T18:19:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.