{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/provably-fair-representations","title":"Provably Fair Representations","arxiv_id":"1710.04394","date":"2017-10-12","proceeding":null,"authors":["Daniel McNamara","Cheng Soon Ong","Robert C. Williamson"],"abstract":"Machine learning systems are increasingly used to make decisions about\npeople's lives, such as whether to give someone a loan or whether to interview\nsomeone for a job. This has led to considerable interest in making such machine\nlearning systems fair. One approach is to transform the input data used by the\nalgorithm. This can be achieved by passing each input data point through a\nrepresentation function prior to its use in training or testing. Techniques for\nlearning such representation functions from data have been successful\nempirically, but typically lack theoretical fairness guarantees. We show that\nit is possible to prove that a representation function is fair according to\ncommon measures of both group and individual fairness, as well as useful with\nrespect to a target task. These provable properties can be used in a governance\nmodel involving a data producer, a data user and a data regulator, where there\nis a separation of concerns between fairness and target task utility to ensure\ntransparency and prevent perverse incentives. We formally define the 'cost of\nmistrust' of using this model compared to the setting where there is a single\ntrusted party, and provide bounds on this cost in particular cases. We present\na practical approach to learning fair representation functions and apply it to\nfinancial and criminal justice datasets. We evaluate the fairness and utility\nof these representation functions using measures motivated by our theoretical\nresults.","url_abs":"http://arxiv.org/abs/1710.04394v1","url_pdf":"http://arxiv.org/pdf/1710.04394v1.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":"provably-fair-representations","repo_url":"https://github.com/eth-sri/lcifr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.04394","atlas_url":"https://app.syntology.ai/?focus=1710.04394","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1710.04394"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1710.04394\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1710.04394"},"call":"get_concepts_for_paper(arxiv_id=\"1710.04394\")"}],"by_repo":[{"repo":"eth-sri/lcifr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2002.10312"],"harvested_for_calls":[{"arxiv_id":"2002.10312","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.10312"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.10312\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b5cafa8e2bd9c1665d2fdddaf604241c60853e1d57b9edf2e5c33c2ee6e0ac78","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}