Fairkit-learn: A Fairness Evaluation and Comparison Toolkit
by Brittany Johnson, Yuriy Brun
Abstract:
Advances in how we build and use software, specifically the integration of machine learning for decision making, have led to widespread concern around model and software fairness. We present fairkit-learn, an interactive Python toolkit designed to support data scientists' ability to reason about and understand model fairness. We outline how fairkit-learn can support model training, evaluation, and comparison and describe the potential benefit that comes with using fairkit-learn in comparison to the state-of-the-art. Fairkit-learn is open source at https://go.gmu.edu/fairkit-learn/.
View PDF
Citation:
Brittany Johnson and Yuriy Brun, Fairkit-learn: A Fairness Evaluation and Comparison Toolkit, in Proceedings of the Demonstrations Track at the 44th International Conference on Software Engineering (ICSE), 2022, pp. 70–74.
Bibtex:
@inproceedings{Johnson22,
  author = {Brittany Johnson and Yuriy Brun},
  title =
  {\href{http://people.cs.umass.edu/brun/pubs/pubs/Johnson22.pdf}{Fairkit-learn: {A} 
    Fairness Evaluation and Comparison Toolkit}}, 
  booktitle = {Proceedings of the Demonstrations Track at the 44th
    International Conference on Software Engineering (ICSE)},  
  venue = {ICSE Demo},
  address = {Pittsburgh, PA, USA},
  month = {May},
  date = {22--27},
  year = {2022},
  pages = {70--74},
  doi = {10.1145/3510454.3516830},  
  note = {\href{https://doi.org/10.1145/3510454.3516830}{DOI: 10.1145/3510454.3516830}},
  
  accept = {$\frac{49}{98} = 50\%$},

  abstract = {Advances in how we build and use software, specifically the integration of
  machine learning for decision making, have led to widespread concern around
  model and software fairness. We present fairkit-learn, an interactive Python
  toolkit designed to support data scientists' ability to reason about and
  understand model fairness. We outline how fairkit-learn can support model
  training, evaluation, and comparison and describe the potential benefit that
  comes with using fairkit-learn in comparison to the state-of-the-art.
  Fairkit-learn is open source at https://go.gmu.edu/fairkit-learn/.},

  fundedBy = {NSF CCF-1763423, Google, Meta Platforms, and Kosa.ai},
}