{"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/latent-space-smoothing-for-individually-fair-1","title":"Latent Space Smoothing for Individually Fair Representations","arxiv_id":"2111.13650","date":"2021-11-26","proceeding":null,"authors":["Momchil Peychev","Anian Ruoss","Mislav Balunović","Maximilian Baader","Martin Vechev"],"abstract":"Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair representations, i.e., guaranteeing that similar individuals are treated similarly, remains challenging in high-dimensional settings such as computer vision. In this work, we introduce LASSI, the first representation learning method for certifying individual fairness of high-dimensional data. Our key insight is to leverage recent advances in generative modeling to capture the set of similar individuals in the generative latent space. This enables us to learn individually fair representations that map similar individuals close together by using adversarial training to minimize the distance between their representations. Finally, we employ randomized smoothing to provably map similar individuals close together, in turn ensuring that local robustness verification of the downstream application results in end-to-end fairness certification. Our experimental evaluation on challenging real-world image data demonstrates that our method increases certified individual fairness by up to 90% without significantly affecting task utility.","url_abs":"https://arxiv.org/abs/2111.13650v3","url_pdf":"https://arxiv.org/pdf/2111.13650v3.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":"latent-space-smoothing-for-individually-fair-1","repo_url":"https://github.com/eth-sri/lassi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.13650","atlas_url":"https://app.syntology.ai/?focus=2111.13650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13650"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eth-sri/lassi","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"dcbbd3ad40bafc79","entry":"argslist_int","repo":"eth-sri/lassi","repo_kind":"official","path":"src/args.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/args.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dcbbd3ad40bafc79"}},{"code_sha256_prefix":"60bbf1755c1ebda3","entry":"argslist_str","repo":"eth-sri/lassi","repo_kind":"official","path":"src/args.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/args.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60bbf1755c1ebda3"}},{"code_sha256_prefix":"8560848ba2fe7200","entry":"bool_flag","repo":"eth-sri/lassi","repo_kind":"official","path":"src/args.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/args.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8560848ba2fe7200"}},{"code_sha256_prefix":"a4d5569afce3d5a8","entry":"get_device","repo":"eth-sri/lassi","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4d5569afce3d5a8"}},{"code_sha256_prefix":"cbc4f68dc516b53f","entry":"get_or_create_path","repo":"eth-sri/lassi","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cbc4f68dc516b53f"}},{"code_sha256_prefix":"bedd06b1b2d62203","entry":"l2_dist","repo":"eth-sri/lassi","repo_kind":"official","path":"src/certification/center_smoothing.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/certification/center_smoothing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bedd06b1b2d62203"}},{"code_sha256_prefix":"cbbac27e333d24a9","entry":"repeat_along_dim","repo":"eth-sri/lassi","repo_kind":"official","path":"src/certification/center_smoothing.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/certification/center_smoothing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cbbac27e333d24a9"}},{"code_sha256_prefix":"b720ce2242296694","entry":"get_path_to","repo":"eth-sri/lassi","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/eth-sri/lassi/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b720ce2242296694"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}