Assessing and Enforcing Fairness in the AI Lifecycle

Abstract

A significant challenge in detecting and mitigating bias is creating a mindset amongst AI developers to address unfairness. The current literature on fairness is broad, and the learning curve to distinguish where to use existing metrics and techniques for bias detection or mitigation is difficult. This survey systematises the state-of-the-art about distinct notions of fairness and relative techniques for bias mitigation according to the AI lifecycle. Gaps and challenges identified during the development of this work are also discussed.

Cite

Text

Calegari et al. "Assessing and Enforcing Fairness in the AI Lifecycle." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/735

Markdown

[Calegari et al. "Assessing and Enforcing Fairness in the AI Lifecycle." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/calegari2023ijcai-assessing/) doi:10.24963/IJCAI.2023/735

BibTeX

@inproceedings{calegari2023ijcai-assessing,
  title     = {{Assessing and Enforcing Fairness in the AI Lifecycle}},
  author    = {Calegari, Roberta and Castañé, Gabriel G. and Milano, Michela and O'Sullivan, Barry},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {6554-6562},
  doi       = {10.24963/IJCAI.2023/735},
  url       = {https://mlanthology.org/ijcai/2023/calegari2023ijcai-assessing/}
}