Counterfactual Risk Assessments, Evaluation, and Fairness

Coston, Amanda; Mishler, Alan; Kennedy, Edward H.; Chouldechova, Alexandra

doi:10.48550/arxiv.1909.00066

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After a period of theoretical research, a collaboration with the municipality of Amsterdam and Statistics Netherlands (CBS) was started in order to study a relevant problem with real data. After finishing the thesis 7 , the research continued as part of a project on fair algorithms. This project was carried out in a collaboration between CBS, municipality of Amsterdam, the University of Amsterdam, codefor.nl, the Association of Netherlands Municipalities (VNG) and other Dutch municipalities and was funded by the Ministry of the Interior and Kingdom Relations (BZK).…”

Section: Acknowledgments and Disclosure Of Fundingmentioning

confidence: 99%

“…Wachter et al [43] and Mothilal et al [26] aim to generate a set of counterfactual input points which leads to a different outcome of the model, without explicitly modelling causal mechanisms among attributes. Coston et al [7] suggest using counterfactual data to evaluate models on counterfactual fairness, but do not account for unobserved confounders and focus on treatment based counterfactuals rather than path specific effects.…”

Section: Appendixmentioning

confidence: 99%

See 1 more Smart Citation

Improving Fair Predictions Using Variational Inference In Causal Models

Helwegen¹,

Louizos²,

Forré³

2020

Preprint

View full text Add to dashboard Cite

The importance of algorithmic fairness grows with the increasing impact machine learning has on people's lives. Recent work on fairness metrics shows the need for causal reasoning in fairness constraints. In this work, a practical method named FairTrade is proposed for creating flexible prediction models which integrate fairness constraints on sensitive causal paths. The method uses recent advances in variational inference in order to account for unobserved confounders. Further, a method outline is proposed which uses the causal mechanism estimates to audit black box models. Experiments are conducted on simulated data and on a real dataset in the context of detecting unlawful social welfare. This research aims to contribute to machine learning techniques which honour our ethical and legal boundaries.

show abstract

Section: Acknowledgments and Disclosure Of Fundingmentioning

confidence: 99%

Section: Appendixmentioning

confidence: 99%

Improving Fair Predictions Using Variational Inference In Causal Models

Helwegen¹,

Louizos²,

Forré³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…These approaches require making untestable assumptions. Of particular note is the observation in Coston et al (2019) that fairness-adjustment procedures based on Y in settings with treatment effects may lead to adverse outcomes. To apply our method in such settings, we would need to match conditional counterfactual distributions, which could be a direction of future research.…”

Section: Related Workmentioning

confidence: 99%

Conditional Learning of Fair Representations

Han¹,

Coston²,

Adel³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups. Two key components underpinning the design of our algorithm are balanced error rate and conditional alignment of representations. We show how these two components contribute to ensuring accuracy parity and equalized false-positive and false-negative rates across groups without impacting demographic parity. Furthermore, we also demonstrate both in theory and on two real-world experiments that the proposed algorithm leads to a better utility-fairness trade-off on balanced datasets compared with existing algorithms on learning fair representations.

show abstract

Counterfactual Risk Assessments, Evaluation, and Fairness

Cited by 2 publications

References 0 publications

Improving Fair Predictions Using Variational Inference In Causal Models

Improving Fair Predictions Using Variational Inference In Causal Models

Conditional Learning of Fair Representations

Contact Info

Product

Resources

About