• Corpus ID: 3352595

Avoiding Discrimination through Causal Reasoning

@article{Kilbertus2017AvoidingDT,
  title={Avoiding Discrimination through Causal Reasoning},
  author={Niki Kilbertus and Mateo Rojas-Carulla and Giambattista Parascandolo and Moritz Hardt and Dominik Janzing and Bernhard Sch{\"o}lkopf},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.02744}
}
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.

Figures from this paper

Survey on Causal-based Machine Learning Fairness Notions
TLDR
This paper examines an exhaustive list of causal-based fairness notions, in particular their applicability in real-world scenarios and compiles the most relevant identifiability criteria for the problem of fairness from the extensive literature on identifiable theory.
On the Fairness of Causal Algorithmic Recourse
TLDR
Two new fairness criteria at the group and individual level are proposed which are based on a causal framework that explicitly models relationships between input features, thereby allowing to capture downstream effects of recourse actions performed in the physical world.
Causal Interventions for Fairness
TLDR
This work uses causal methods to model the effects of interventions, allowing for potential interference--each individual's outcome may depend on who else receives the intervention, and demonstrates this with an example of allocating a budget of teaching resources using a dataset of schools in New York City.
A Causal Look at Statistical Definitions of Discrimination
TLDR
It is proved that when the base rates differ across the protected groups and there is no perfect separation, then a standard classifier cannot achieve exact predictive parity, and the amount of disparate mistreatment for the positive predictive value metric is proportional to the difference between the base rate.
Causal Discovery for Fairness
TLDR
It is shown how different causal discovery approaches may result in different causal models and, most importantly, how even slight differences between causal models can have significant impact on fairness/discrimination conclusions.
Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
TLDR
This work uses the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT and shows that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.
Eliminating Latent Discrimination: Train Then Mask
TLDR
This paper defines a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistics and econometrics, and establishes analytical and algorithmic results about the existence of a fair classifier in the context of supervised learning.
The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
TLDR
It is argued that it is often preferable to treat similarly risky people similarly, based on the most statistically accurate estimates of risk that one can produce, rather than requiring that algorithms satisfy popular mathematical formalizations of fairness.
Fairness through Equality of Effort
TLDR
A new causal-based fairness notation, called equality of effort, is developed that helps answer questions like to what extend a legitimate variable should change to make a particular individual achieve a certain outcome level and addresses the concerns whether the efforts made to achieve the same outcome level for individuals from the protected group and that from the unprotected group are different.
Counterfactual Fairness
TLDR
This paper develops a framework for modeling fairness using tools from causal inference and demonstrates the framework on a real-world problem of fair prediction of success in law school.
...
...

References

SHOWING 1-10 OF 23 REFERENCES
Counterfactual Fairness
TLDR
This paper develops a framework for modeling fairness using tools from causal inference and demonstrates the framework on a real-world problem of fair prediction of success in law school.
Exposing the probabilistic causal structure of discrimination
TLDR
This paper defines a method to extract, from a dataset of historical decision records, the causal structures existing among the attributes in the data, and develops a type of constrained Bayesian network, which it dubs Suppes-Bayes causal network (SBCN).
Fair Inference on Outcomes
TLDR
It is argued that the existence of discrimination can be formalized in a sensible way as the presence of an effect of a sensitive covariate on the outcome along certain causal pathways, a view which generalizes (Pearl 2009).
Fairness in Criminal Justice Risk Assessments: The State of the Art
Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this article, we seek to clarify
Anti-discrimination learning: a causal modeling-based framework
  • Lu Zhang, Xintao Wu
  • Computer Science
    International Journal of Data Science and Analytics
  • 2017
TLDR
A causal modeling-based framework for anti-discrimination learning is introduced, two works for discovering and preventing both direct and indirect system-level discrimination in the training data, and a work for extending the non-discrimination result from theTraining data to prediction.
Certifying and Removing Disparate Impact
TLDR
This work links disparate impact to a measure of classification accuracy that while known, has received relatively little attention and proposes a test for disparate impact based on how well the protected class can be predicted from the other attributes.
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
TLDR
A new notion of unfairness, disparate mistreatment, is introduced, defined in terms of misclassification rates, which is proposed for decision boundary-based classifiers and can be easily incorporated into their formulation as convex-concave constraints.
Inherent Trade-Offs in the Fair Determination of Risk Scores
TLDR
Some of the ways in which key notions of fairness are incompatible with each other are suggested, and hence a framework for thinking about the trade-offs between them is provided.
Fairness Constraints: Mechanisms for Fair Classification
TLDR
This paper introduces a flexible mechanism to design fair classifiers by leveraging a novel intuitive measure of decision boundary (un)fairness, and shows on real-world data that this mechanism allows for a fine-grained control on the degree of fairness, often at a small cost in terms of accuracy.
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
TLDR
It is demonstrated that the criteria cannot all be simultaneously satisfied when recidivism prevalence differs across groups, and how disparate impact can arise when an RPI fails to satisfy the criterion of error rate balance.
...
...