Corpus ID: 3352595

Avoiding Discrimination through Causal Reasoning

@inproceedings{Kilbertus2017AvoidingDT,
  title={Avoiding Discrimination through Causal Reasoning},
  author={Niki Kilbertus and Mateo Rojas-Carulla and Giambattista Parascandolo and Moritz Hardt and D. Janzing and B. Sch{\"o}lkopf},
  booktitle={NIPS},
  year={2017}
}
Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. [...] Key Method First, we crisply articulate why and when observational criteria fail, thus formalizing what was before a matter of opinion. Second, our approach exposes previously ignored subtleties and why they are fundamental to the problem. Finally, we put forward natural causal non-discrimination criteria and develop algorithms that satisfy them.Expand
Causal Interventions for Fairness
A Causal Look at Statistical Definitions of Discrimination
Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
Eliminating Latent Discrimination: Train Then Mask
The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
Fairness through Equality of Effort
Counterfactual Fairness
The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 24 REFERENCES
Counterfactual Fairness
Exposing the probabilistic causal structure of discrimination
Fair Inference on Outcomes
Fairness in Criminal Justice Risk Assessments: The State of the Art
Anti-discrimination learning: a causal modeling-based framework
  • L. Zhang, Xintao Wu
  • Computer Science
  • International Journal of Data Science and Analytics
  • 2017
Inherent Trade-Offs in the Fair Determination of Risk Scores
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
...
1
2
3
...