@inproceedings{nokey,

title = {Fairness without the sensitive attribute via Causal Variational Autoencoder},

author = {Vincent Grari and Sylvain Lamprier and Marcin Detyniecki},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

journal = {2022 International Joint Conferences on Artificial Intelligence Organization (IJCAI)},

abstract = {In recent years, most fairness strategies in machine learning models focus on mitigating unwanted biases by assuming that the sensitive information is observed. However this is not always possible in practice. Due to privacy purposes and var-ious regulations such as RGPD in EU, many personal sensitive attributes are frequently not collected. We notice a lack of approaches for mitigating bias in such difficult settings, in particular for achieving classical fairness objectives such as Demographic Parity and Equalized Odds. By leveraging recent developments for approximate inference, we propose an approach to fill this gap. Based on a causal graph, we rely on a new variational auto-encoding based framework named SRCVAE to infer a sensitive information proxy, that serve for bias mitigation in an adversarial fairness approach. We empirically demonstrate significant improvements over existing works in the field. We observe that the generated proxy's latent space recovers sensitive information and that our approach achieves a higher accuracy while obtaining the same level of fairness on two real datasets, as measured using com-mon fairness definitions.},

keywords = {Fairness},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grari2021fairness,

title = {Fairness-aware neural Rényi minimization for continuous features},

author = {Vincent Grari and Sylvain Lamprier and Marcin Detyniecki},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence},

pages = {2262--2268},

keywords = {Fairness},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grari2021enforcing,

title = {Enforcing Individual Fairness via Rényi Variational Inference},

author = {Vincent Grari and Oualid El Hajouji and Sylvain Lamprier and Marcin Detyniecki},

year  = {2021},

date = {2021-01-01},

booktitle = {International Conference on Neural Information Processing},

pages = {608--616},

organization = {Springer},

keywords = {Fairness},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grari2021learning,

title = {Learning Unbiased Representations via Rényi Minimization},

author = {Vincent Grari and Oualid El Hajouji and Sylvain Lamprier and Marcin Detyniecki},

year  = {2021},

date = {2021-01-01},

booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases},

pages = {749--764},

organization = {Springer},

keywords = {Fairness},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grari2019fair,

title = {Fair adversarial gradient tree boosting},

author = {Vincent Grari and Boris Ruf and Sylvain Lamprier and Marcin Detyniecki},

year  = {2019},

date = {2019-01-01},

booktitle = {2019 IEEE International Conference on Data Mining (ICDM)},

pages = {1060--1065},

organization = {IEEE},

keywords = {Fairness},

pubstate = {published},

tppubtype = {inproceedings}

}