{"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/learning-fair-representations-via-an","title":"Learning Fair Representations via an Adversarial Framework","arxiv_id":"1904.13341","date":"2019-04-30","proceeding":null,"authors":["Rui Feng","Yang Yang","Yuehan Lyu","Chenhao Tan","Yizhou Sun","Chunping Wang"],"abstract":"Fairness has become a central issue for our research community as\nclassification algorithms are adopted in societally critical domains such as\nrecidivism prediction and loan approval. In this work, we consider the\npotential bias based on protected attributes (e.g., race and gender), and\ntackle this problem by learning latent representations of individuals that are\nstatistically indistinguishable between protected groups while sufficiently\npreserving other information for classification. To do that, we develop a\nminimax adversarial framework with a generator to capture the data distribution\nand generate latent representations, and a critic to ensure that the\ndistributions across different protected groups are similar. Our framework\nprovides a theoretical guarantee with respect to statistical parity and\nindividual fairness. Empirical results on four real-world datasets also show\nthat the learned representation can effectively be used for classification\ntasks such as credit risk prediction while obstructing information related to\nprotected groups, especially when removing protected attributes is not\nsufficient for fair classification.","url_abs":"http://arxiv.org/abs/1904.13341v1","url_pdf":"http://arxiv.org/pdf/1904.13341v1.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":"learning-fair-representations-via-an","repo_url":"https://github.com/rhythmswing/Fair-Representation-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.13341","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}