{"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/beyond-the-selected-completely-at-random","title":"Beyond the Selected Completely At Random Assumption for Learning from Positive and Unlabeled Data","arxiv_id":"1809.03207","date":"2018-09-10","proceeding":null,"authors":["Jessa Bekker","Pieter Robberechts","Jesse Davis"],"abstract":"Most positive and unlabeled data is subject to selection biases. The labeled examples can, for example, be selected from the positive set because they are easier to obtain or more obviously positive. This paper investigates how learning can be ena BHbled in this setting. We propose and theoretically analyze an empirical-risk-based method for incorporating the labeling mechanism. Additionally, we investigate under which assumptions learning is possible when the labeling mechanism is not fully understood and propose a practical method to enable this. Our empirical analysis supports the theoretical results and shows that taking into account the possibility of a selection bias, even when the labeling mechanism is unknown, improves the trained classifiers.","url_abs":"https://arxiv.org/abs/1809.03207v4","url_pdf":"https://arxiv.org/pdf/1809.03207v4.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":"beyond-the-selected-completely-at-random","repo_url":"https://github.com/ML-KULeuven/SAR-PU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"selection-bias","task_name":"Selection bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.03207"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ML-KULeuven/SAR-PU","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":20},"by_repo_kind":{"listed":{"samples":20,"ran":0,"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":"392b682dd10b9a9b","entry":"accuracy","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/evaluation.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"392b682dd10b9a9b"}},{"code_sha256_prefix":"3d1135a1974c4aa5","entry":"binarize","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/data_processing.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/data_processing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d1135a1974c4aa5"}},{"code_sha256_prefix":"c7b90aa51789cfcf","entry":"compute_best_rbf_kernel_width","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"lib/km/km/Kernel_MPE_grad_threshold.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/lib/km/km/Kernel_MPE_grad_threshold.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7b90aa51789cfcf"}},{"code_sha256_prefix":"be88997e62f65795","entry":"copy_if_possible","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/experiments.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/experiments.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be88997e62f65795"}},{"code_sha256_prefix":"ec7fc63d99c0d644","entry":"fp","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/evaluation.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec7fc63d99c0d644"}},{"code_sha256_prefix":"8a181ed99567fe3c","entry":"generate_attributes","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/data_extending.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/data_extending.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a181ed99567fe3c"}},{"code_sha256_prefix":"e444fb0eb2e6bef5","entry":"keep_k_most_common","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/data_processing.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/data_processing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e444fb0eb2e6bef5"}},{"code_sha256_prefix":"8182fdee9c3c4d2a","entry":"label_data","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/labeling_mechanisms.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/labeling_mechanisms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8182fdee9c3c4d2a"}},{"code_sha256_prefix":"1ff62228d9b009fc","entry":"low_c","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"lib/tice/tice/tice.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/lib/tice/tice/tice.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ff62228d9b009fc"}},{"code_sha256_prefix":"58f045c773108472","entry":"max_bepp","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"lib/tice/tice/tice.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/lib/tice/tice/tice.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58f045c773108472"}},{"code_sha256_prefix":"24699e61a8913eef","entry":"original_data_path","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/paths_and_names.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/paths_and_names.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24699e61a8913eef"}},{"code_sha256_prefix":"3719d8c26afdaba8","entry":"parse_cl_atts","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/experiments.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/experiments.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3719d8c26afdaba8"}},{"code_sha256_prefix":"7d4cfbc0e8c0918d","entry":"parse_labeling_model","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/labeling_mechanisms.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/labeling_mechanisms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d4cfbc0e8c0918d"}},{"code_sha256_prefix":"485e31dbab6c48df","entry":"parse_propensity_attributes","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/__main__.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/__main__.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"485e31dbab6c48df"}},{"code_sha256_prefix":"1c4ebff91cd1fdaf","entry":"parse_settings","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/experiments.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/experiments.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c4ebff91cd1fdaf"}},{"code_sha256_prefix":"d7dcbcf5040563af","entry":"partitions_data_path","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/paths_and_names.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/paths_and_names.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7dcbcf5040563af"}},{"code_sha256_prefix":"50b21e7e6829bc67","entry":"pick_delta","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"lib/tice/tice/tice.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/lib/tice/tice/tice.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50b21e7e6829bc67"}},{"code_sha256_prefix":"8b3e0aaca0e07859","entry":"processed_data_path","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/paths_and_names.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/paths_and_names.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b3e0aaca0e07859"}},{"code_sha256_prefix":"93af1f21100c125e","entry":"read_data","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/input_output.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/input_output.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93af1f21100c125e"}},{"code_sha256_prefix":"d88647279680aeec","entry":"tp","repo":"ML-KULeuven/SAR-PU","repo_kind":"listed","path":"sarpu/sarpu/evaluation.py","file_url":"https://github.com/ML-KULeuven/SAR-PU/blob/HEAD/sarpu/sarpu/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d88647279680aeec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}