logseq/pages/@A Survey on Bias and Fairness in Machine Learning.md

tags:: ReadingNotes #bias #fairness #machinelearning date:: 31-07-2022 issn:: "0360-0300, 1557-7341" issue:: 6 doi:: 10.1145/3457607 title:: @A Survey on Bias and Fairness in Machine Learning pages:: 1-35 volume:: 54 item-type:: journalArticle access-date:: 2023-02-18T07:10:49Z original-title:: A Survey on Bias and Fairness in Machine Learning language:: en url:: https://dl.acm.org/doi/10.1145/3457607 publication-title:: ACM Computing Surveys journal-abbreviation:: ACM Comput. Surv. authors:: Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan library-catalog:: DOI.org (Crossref) links:: Local library, Web library]

• Abstract
  • With 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 environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.
• Attachments
  • Mehrabi et al. - 2022 - A Survey on Bias and Fairness in Machine Learning.pdf {{zotero-imported-file VHPDAFE3, "Mehrabi et al. - 2022 - A Survey on Bias and Fairness in Machine Learning.pdf"}}
• Highlights
  • ((6449054a-bea4-4b8c-9878-d490a823bb9f))
  • In the context of decision-making fairness is:
    • ((64490984-7bb9-4f37-acc7-a0e9b92755af)) definition
  • Potential sources of unfairness in machine learning outcomes arise from ==biases in the data== and ==those that arise from algorithms==.
  • #+BEGIN_IMPORTANT ((64490b15-3caf-43ed-8eb9-5a097962942d)) #+END_IMPORTANT
  • #+BEGIN_QUOTE ((64491040-2bef-4c75-ac2c-24a4375dc08e)) #+END_QUOTE
  • ((644913fd-f97d-46cc-94ae-504f5d4cdfbb))
  • Reference papers to see:
    • ((64491361-223a-4d46-b120-9e81f0226d1e))
    • ((6449137d-1640-497d-86be-184627860674))
  • #+BEGIN_IMPORTANT Possiamo dire quindi che bias e' una motivazione/source di unfairness Noi ci focalizziamo sulla definizione di fairness focalizzandoci su biases in data #+END_IMPORTANT
  • ((64491956-8fb9-45f0-8472-81aaafe147f5))
  • ((64491a84-f0c7-4bbc-af7c-2c8fc605f702))

  • ((644a347e-bcf2-4675-8d5e-6e86cbc7b9d9))