A Causal Bayesian Networks Viewpoint on Fairness

By Silvia Chiappa, William S. Isaac. 2018

68 citations recorded by the source corpus.

We offer a graphical interpretation of unfairness in a dataset as the presence of an unfair causal effect of the sensitive attribute in the causal Bayesian network representing the data-generation mechanism. We use this viewpoint to revisit the recent debate surrounding the COMPAS pretrial risk assessment tool and, more generally, to point out that fairness evaluation on a model requires careful considerations on the patterns of unfairness underlying the training data. We show that causal Bayesian networks provide us with a powerful tool to measure unfairness in a dataset and to design fair models in complex unfairness scenarios.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation (2019, background): “, 2012), counterfactual fairness requires the same model predictions before and after intervention on sensitive attributes in data-generating causal graphs (Kusner et al., 2017; Kilbertus et al., 2017; Chiappa, 2019; Chiappa and Isaac, 2019).”
Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence (2020, background): “Such questions speak to a critical practice whose recent efforts, in response, have proposed fairness metrics that attempt to use causality (Chiappa and Isaac, 2018; Mitchell et al., 2018; Nabi and Shpitser, 2018; Madras et al., 2019) or interactivity (Canetti et al.”
Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics (2020, background): “…(SCMs) and Causal Bayesian Networks (CBNs) that have been recently proposed to model causality in ML problem formulation (Madras et al., 2019; Chiappa & Isaac, 2018), CBSD is founded upon a system dynamics (SD) (Hovmand, 2014a) approach, which takes a characteristically feedback approach to…”
Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation (2022, background): “There is also a vast literature discussing counterfactuals, a type of synthetic example steeped in causality, and which have long been used to detect forms of discrimination [20, 86].”
Causality matters in medical imaging (2019, background): “Interestingly, the same formalism of causal reasoning explored here was also shown to be especially well-suited for expressing and addressing issues of unfairness (e.g. social biases) 62 and dataset shift 63 in other contexts.”
A Review on Fairness in Machine Learning (2022, background): “[14] and Chiappa and Isaac [45] for the relationships between causality and fairness.”
A General Approach to Fairness with Optimal Transport (2020, methodology): “We discuss input transportation in the PSCF context corresponding to the CBN on the left, in which red links indicate unfair inﬂuence from A .”
Fairness in Machine Learning: A Survey (2020, background): “A key objective is to uncover causal relationships in the data and find dependencies between sensitive and non-sensitive variables [106, 163, 173, 63, 110, 208, 234].”
Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context (2020, methodology): “ to be made. Often times these causal diagrams are constructed using directed acyclic graphs (DAGs). A number of these approaches leverage Structural Causal Models (SCMs) and Causal Bayesian Networks [18, 62] for measuring unfairness in datasets or building fair decision making models that have bias”