On the Fairness of Causal Algorithmic Recourse

By Julius von Kügelgen, Umang Bhatt, Amir-Hossein Karimi, Isabel Valera, Adrian Weller, Bernhard Schölkopf. 2020

105 citations recorded by the source corpus.

Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing 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 study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.

Subfields: Cognitive Neuroscience, Safety Research, Causal Inference & Discovery, AI Ethics, Fairness & Society

How researchers see this paper

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

In Cognitive Neuroscience

1. Nan Rosemary Ke
2. Anirudh Goyal
3. Stefan Bauer
4. Yoshua Bengio
5. Bernhard Schölkopf
6. Nal Kalchbrenner
7. Dominik Janzing

In Safety Research

1. Julius von Kügelgen
2. Bernhard Schölkopf
3. Amir-Hossein Karimi
4. Isabel Valera
5. Stefan Bauer
6. Yoshua Bengio
7. Anirudh Goyal
8. R. Teal Witter

In Causal Inference & Discovery

1. Yoshua Bengio
2. Anirudh Goyal
3. Stefan Bauer
4. Francesco Locatello
5. Nan Rosemary Ke
6. Nal Kalchbrenner
7. Bernhard Schölkopf
8. Julius von Kügelgen

In AI Ethics, Fairness & Society

1. Bernhard Schölkopf
2. Isabel Valera
3. Amir-Hossein Karimi
4. R. Teal Witter
5. Lucas Rosenblatt
6. Julius von Kügelgen
7. Francesco Locatello

Citations in the corpus

• Toward Causal Representation Learning (2021, background): “the general goal of modern machine learning to learn meaningful representations of data, where meaningful can include robust, explainable, or fair [130], [134], [142], [259], [275].”
• Towards Causal Representation Learning (2021, neutral): “include robust, explainable, or fair [142, 133, 276, 130, 260].”
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (2020, background): “The importance of causal reasoning for an ethical and socially beneficial use of ML-assisted technology has also been stressed in a number of recent works in the field of explainability and fair algorithmic decision making [29, 42, 24, 63, 64, 10, 57, 15].”
• Counterfactual Fairness Is Basically Demographic Parity (2022, background): “…modify only slightly Definition 2 to enable training classifiers and other decision making algorithms (Zhang and Bareinboim 2018; Chiappa 2019; Wu, Zhang, and Wu 2019; Coston et al. 2020; Black, Yeom, and Fredrikson 2020; Mhasawade and Chunara 2021; Chikahara et al. 2021; von K¨ugelgen et al. 2022).”
• Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “[322] extend this fairness notion when the distance between the recourse is measured in a causal manner.”