{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/predict-responsibly-improving-fairness-and","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","arxiv_id":"1711.06664","date":"2017-11-17","proceeding":"NeurIPS 2018 12","authors":["David Madras","Toniann Pitassi","Richard Zemel"],"abstract":"In many machine learning applications, there are multiple decision-makers\ninvolved, both automated and human. The interaction between these agents often\ngoes unaddressed in algorithmic development. In this work, we explore a simple\nversion of this interaction with a two-stage framework containing an automated\nmodel and an external decision-maker. The model can choose to say \"Pass\", and\npass the decision downstream, as explored in rejection learning. We extend this\nconcept by proposing \"learning to defer\", which generalizes rejection learning\nby considering the effect of other agents in the decision-making process. We\npropose a learning algorithm which accounts for potential biases held by\nexternal decision-makers in a system. Experiments demonstrate that learning to\ndefer can make systems not only more accurate but also less biased. Even when\nworking with inconsistent or biased users, we show that deferring models still\ngreatly improve the accuracy and/or fairness of the entire system.","url_abs":"http://arxiv.org/abs/1711.06664v3","url_pdf":"http://arxiv.org/pdf/1711.06664v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predict-responsibly-improving-fairness-and","repo_url":"https://github.com/dmadras/predict-responsibly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.06664","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}