Log In Sign Up

On the Fairness of Causal Algorithmic Recourse

by   Julius von Kügelgen, et al.

While many recent works have studied the problem of algorithmic fairness from the perspective of predictions, here we investigate the fairness of recourse actions recommended to individuals to recover from an unfavourable classification. To this end, we propose two new fairness criteria at the group and individual level which—unlike prior work on equalising the average distance from the decision boundary across protected groups—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. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We then investigate how to enforce fair recourse in the training of the classifier. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions and structural changes to the system, as opposed to constraints on the classifier.


page 1

page 2

page 3

page 4


Disentangled Representation with Causal Constraints for Counterfactual Fairness

Much research has been devoted to the problem of learning fair represent...

Provably Training Neural Network Classifiers under Fairness Constraints

Training a classifier under fairness constraints has gotten increasing a...

Fairness and robustness in anti-causal prediction

Robustness to distribution shift and fairness have independently emerged...

Fair Data Adaptation with Quantile Preservation

Fairness of classification and regression has received much attention re...

Causal Interventions for Fairness

Most approaches in algorithmic fairness constrain machine learning metho...

Beyond Individual and Group Fairness

We present a new data-driven model of fairness that, unlike existing sta...

The effects of algorithmic flagging on fairness: quasi-experimental evidence from Wikipedia

Online community moderators often rely on social signals like whether or...