{"alternative_title":["Advances in Neural Information Processing Systems"],"publication_identifier":{"isbn":["9781713871088"]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"ista":"Lohaus M, Kleindessner M, Kenthapadi K, Locatello F, Russell C. 2022. Are two heads the same as one? Identifying disparate treatment in fair neural networks. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 35, 16548–16562.","mla":"Lohaus, Michael, et al. “Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks.” <i>36th Conference on Neural Information Processing Systems</i>, vol. 35, Neural Information Processing Systems Foundation, 2022, pp. 16548–62.","ama":"Lohaus M, Kleindessner M, Kenthapadi K, Locatello F, Russell C. Are two heads the same as one? Identifying disparate treatment in fair neural networks. In: <i>36th Conference on Neural Information Processing Systems</i>. Vol 35. Neural Information Processing Systems Foundation; 2022:16548-16562.","short":"M. Lohaus, M. Kleindessner, K. Kenthapadi, F. Locatello, C. Russell, in:, 36th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2022, pp. 16548–16562.","ieee":"M. Lohaus, M. Kleindessner, K. Kenthapadi, F. Locatello, and C. Russell, “Are two heads the same as one? Identifying disparate treatment in fair neural networks,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, LA, United States, 2022, vol. 35, pp. 16548–16562.","apa":"Lohaus, M., Kleindessner, M., Kenthapadi, K., Locatello, F., &#38; Russell, C. (2022). Are two heads the same as one? Identifying disparate treatment in fair neural networks. In <i>36th Conference on Neural Information Processing Systems</i> (Vol. 35, pp. 16548–16562). New Orleans, LA, United States: Neural Information Processing Systems Foundation.","chicago":"Lohaus, Michael, Matthäus Kleindessner, Krishnaram Kenthapadi, Francesco Locatello, and Chris Russell. “Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks.” In <i>36th Conference on Neural Information Processing Systems</i>, 35:16548–62. Neural Information Processing Systems Foundation, 2022."},"type":"conference","extern":"1","volume":35,"oa_version":"Preprint","external_id":{"arxiv":["2204.04440"]},"date_published":"2022-12-15T00:00:00Z","oa":1,"department":[{"_id":"FrLo"}],"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2204.04440"}],"language":[{"iso":"eng"}],"status":"public","_id":"14106","date_updated":"2023-09-06T10:29:42Z","conference":{"start_date":"2022-11-28","name":"NeurIPS: Neural Information Processing Systems","location":"New Orleans, LA, United States","end_date":"2022-12-09"},"publication":"36th Conference on Neural Information Processing Systems","year":"2022","title":"Are two heads the same as one? Identifying disparate treatment in fair neural networks","page":"16548-16562","author":[{"first_name":"Michael","full_name":"Lohaus, Michael","last_name":"Lohaus"},{"last_name":"Kleindessner","first_name":"Matthäus","full_name":"Kleindessner, Matthäus"},{"full_name":"Kenthapadi, Krishnaram","first_name":"Krishnaram","last_name":"Kenthapadi"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","first_name":"Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"}],"abstract":[{"lang":"eng","text":"We show that deep networks trained to satisfy demographic parity often do so\r\nthrough a form of race or gender awareness, and that the more we force a network\r\nto be fair, the more accurately we can recover race or gender from the internal state\r\nof the network. Based on this observation, we investigate an alternative fairness\r\napproach: we add a second classification head to the network to explicitly predict\r\nthe protected attribute (such as race or gender) alongside the original task. After\r\ntraining the two-headed network, we enforce demographic parity by merging the\r\ntwo heads, creating a network with the same architecture as the original network.\r\nWe establish a close relationship between existing approaches and our approach\r\nby showing (1) that the decisions of a fair classifier are well-approximated by our\r\napproach, and (2) that an unfair and optimally accurate classifier can be recovered\r\nfrom a fair classifier and our second head predicting the protected attribute. We use\r\nour explicit formulation to argue that the existing fairness approaches, just as ours,\r\ndemonstrate disparate treatment and that they are likely to be unlawful in a wide\r\nrange of scenarios under US law."}],"publisher":"Neural Information Processing Systems Foundation","scopus_import":"1","day":"15","month":"12","intvolume":"        35","quality_controlled":"1","publication_status":"published","date_created":"2023-08-21T12:12:42Z","article_processing_charge":"No"}