Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Teaching Your Models to Play Fair | Global AI Student Conf

Teaching Your Models to Play Fair | Global AI Student Conf

It is very important to ensure fairness while building an AI system that can scale to a large number of users. Thus, I plan to first talk about how fairness is important while building AI apps. I would then go on to talk about how FairLearn helps us in doing so specifically with the easy to use dashboard interface. I plan to show how FairLearn could be used to assess model fairness and how it does so. I would then talk about mitigation strategies with FairLearn so as to remove the biases with state of the art models and compare multiple models to perform this successfully. As time persists I would also show live demos about using FairLearn and Azure ML to assess and mitigate fairness in an AI system.

0d7c1e828ec0afbf29c0d37702c4637d?s=128

Rishit Dagli

December 11, 2020
Tweet

Transcript

  1. Teaching Your Models to Play Fair Rishit Dagli @rishit_dagli

  2. None
  3. None
  4. None
  5. None
  6. None
  7. • Interpretability • Privacy • Security

  8. None
  9. None
  10. None
  11. None
  12. None
  13. None
  14. None
  15. None
  16. None
  17. • Property of a person does not affect outcome

  18. Motivation

  19. None
  20. None
  21. Source: Ziyuan Zhong

  22. None
  23. None
  24. None
  25. None
  26. • Dashboards

  27. • Dashboards

  28. • Dashboards

  29. • Dashboards

  30. • Dashboards

  31. • Dashboards

  32. • Dashboards

  33. • Dashboards • Mitigation strategies

  34. • Dashboards • Mitigation strategies

  35. None
  36. None
  37. bit.ly/fairness-deck

  38. None
  39. Thank You Rishit Dagli @rishit_dagli