Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

• URL: http://arxiv.org/abs/2303.08485v2
• Date: Tue, 20 Feb 2024 17:36:11 GMT
• Title: Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
• Authors: Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Edward Bergman, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter
• Abstract summary: We present a comprehensive overview of different ways in which fairness-related harm can arise. We highlight several open technical challenges for future work in this direction.
• Score: 52.86328317233883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can reproduce, amplify, or even introduce unfairness in our societies, causing harm to (groups of) individuals. In response, researchers have started to propose AutoML systems that jointly optimize fairness and predictive performance to mitigate fairness-related harm. However, fairness is a complex and inherently interdisciplinary subject, and solely posing it as an optimization problem can have adverse side effects. With this work, we aim to raise awareness among developers of AutoML systems about such limitations of fairness-aware AutoML, while also calling attention to the potential of AutoML as a tool for fairness research. We present a comprehensive overview of different ways in which fairness-related harm can arise and the ensuing implications for the design of fairness-aware AutoML. We conclude that while fairness cannot be automated, fairness-aware AutoML can play an important role in the toolbox of ML practitioners. We highlight several open technical challenges for future work in this direction. Additionally, we advocate for the creation of more user-centered assistive systems designed to tackle challenges encountered in fairness work

Related papers

• UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models [5.725785427377439]
  We introduce UniAutoML, a human-centered AutoML framework that unifies AutoML for both discriminative and generative tasks. The human-centered design of UniAutoML innovatively features a conversational user interface (CUI) that facilitates natural language interactions. This design enhances transparency and user control throughout the AutoML training process, allowing users to seamlessly break down or modify the model being trained.
  arXiv  Detail & Related papers  (2024-10-09T17:33:15Z)
• Position: A Call to Action for a Human-Centered AutoML Paradigm [83.78883610871867]
  Automated machine learning (AutoML) was formed around the fundamental objectives of automatically and efficiently configuring machine learning (ML) We argue that a key to unlocking AutoML's full potential lies in addressing the currently underexplored aspect of user interaction with AutoML systems.
  arXiv  Detail & Related papers  (2024-06-05T15:05:24Z)
• Towards Scalable Automated Alignment of LLMs: A Survey [54.820256625544225]
  This paper systematically reviews the recently emerging methods of automated alignment. We categorize existing automated alignment methods into 4 major categories based on the sources of alignment signals. We discuss the essential factors that make automated alignment technologies feasible and effective from the fundamental role of alignment.
  arXiv  Detail & Related papers  (2024-06-03T12:10:26Z)
• The Impossibility of Fair LLMs [59.424918263776284]
  The need for fair AI is increasingly clear in the era of large language models (LLMs) We review the technical frameworks that machine learning researchers have used to evaluate fairness. We develop guidelines for the more realistic goal of achieving fairness in particular use cases.
  arXiv  Detail & Related papers  (2024-05-28T04:36:15Z)
• A Multivocal Literature Review on the Benefits and Limitations of Automated Machine Learning Tools [9.69672653683112]
  We conducted a multivocal literature review, which allowed us to identify 54 sources from the academic literature and 108 sources from the grey literature reporting on AutoML benefits and limitations. Concerning the benefits, we highlight that AutoML tools can help streamline the core steps of ML. We highlight several limitations that may represent obstacles to the widespread adoption of AutoML.
  arXiv  Detail & Related papers  (2024-01-21T01:39:39Z)
• AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks [62.05741061393927]
  We envision that the two fields can radically push the boundaries of each other through tight integration. By highlighting conceivable synergies, but also risks, we aim to foster further exploration at the intersection of AutoML and LLMs.
  arXiv  Detail & Related papers  (2023-06-13T19:51:22Z)
• Benchmarking Automated Machine Learning Methods for Price Forecasting Applications [58.720142291102135]
  We show the possibility of substituting manually created ML pipelines with automated machine learning (AutoML) solutions. Based on the CRISP-DM process, we split the manual ML pipeline into a machine learning and non-machine learning part. We show in a case study for the industrial use case of price forecasting, that domain knowledge combined with AutoML can weaken the dependence on ML experts.
  arXiv  Detail & Related papers  (2023-04-28T10:27:38Z)
• The Roles and Modes of Human Interactions with Automated Machine Learning Systems [7.670270099306412]
  Automated machine learning (AutoML) systems continue to progress in both sophistication and performance. It becomes important to understand the how' and why' of human-computer interaction (HCI) within these frameworks. This review serves to identify key research directions aimed at better facilitating the roles and modes of human interactions with both current and future AutoML systems.
  arXiv  Detail & Related papers  (2022-05-09T09:28:43Z)
• Naive Automated Machine Learning -- A Late Baseline for AutoML [0.0]
  Automated Machine Learning (AutoML) is the problem of automatically finding the pipeline with the best generalization performance on some given dataset. We present Naive AutoML, a very simple solution to AutoML that exploits important meta-knowledge about machine learning problems.
  arXiv  Detail & Related papers  (2021-03-18T19:52:12Z)

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.