Skip to content

08_exercise

Jump to bottom
siposl edited this page Jun 21, 2022 · 3 revisions

🏠   ◀️ 07 | Exercise ⚪ 09 | Exercise ▶️

08 | Exercise - Fairness Metrics and Bias Mitigation Algorithms

14.06.22

In this exercise session, we will discuss fairness metrics and bias mitigation algorithms. Most of them are used in the AI Fairness 360 toolkit, so discussing them should help you with the fourth programming assignment.

Agenda

  • 10:15 - 10:20: Welcome and arrival
  • 10:20 - 10:25: Introductory questions
  • 10:25 - 11:00: Fairness Metrics task
  • 11:00 - 11:40: Bias Mitigation Algorithms task
  • 11:40 - 11:45: Goodbye and outlook

Session notes

Slides for the eighth exercise.

In-exercise Task: Fairness Metrics

The task is discussed during the exercise and the instructions can be found in the session notes.

If you'd like to create a presentation, you may upload it under: hcds-summer-2022/exercise/tasks/ex08/.

Resources

These resources should help with the task for your chosen metric.

In-exercise Task: Bias Mitigation Algorithms

The task is discussed during the exercise and the instructions can be found in the session notes.

Resources

Here are the links to the original papers introducing the algorithms.

You may also make use of this great overview for fairness-aware machine learning5 for your task presentations.

References

1 Calmon, F. P., Wei, D., Vinzamuri, B., Natesan Ramamurthy, K., and Varshney, K. R. Optimized preprocessing for discrimination prevention. In Advances in Neural Information Processing Systems 30, pp. 39924001, Long Beach, USA, December 2017.

2 Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., and Venkatasubramanian, S. Certifying and removing disparate impact. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 259–268, Sydney, Australia, August 2015.

3 Zhang, B. H., Lemoine, B., and Mitchell, M. Mitigating unwanted biases with adversarial learning. In Proc. AAAI/ACM Conf. Artif. Intell., Ethics, Society, New Orleans, USA, February 2018.

4 Kamiran, F., Karim, A., and Zhang, X. Decision theory for discrimination-aware classification. In IEEE International Conference on Data Mining, pp. 924–929, 2012. doi: https://doi.org/10.1109/ICDM.2012.45.

5 Dunkelau, J., Leuschel, M., Fairness-Aware Machine Learning An Extensive Overview

Credits & Licenses

Content is available under Attribution-Share Alike 3.0 Unported unless otherwise noted.

Clone this wiki locally