{"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/rethinking-guidance-information-to-utilize","title":"Rethinking Guidance Information to Utilize Unlabeled Samples:A Label Encoding Perspective","arxiv_id":"2406.02862","date":"2024-06-05","proceeding":null,"authors":["Yulong Zhang","Yuan YAO","Shuhao Chen","Pengrong Jin","Yu Zhang","Jian Jin","Jiangang Lu"],"abstract":"Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples. A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their learning. However, EntMin emphasizes prediction discriminability while neglecting prediction diversity. To alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled samples. By analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label encoding. Inspired by this finding, we propose a Label-Encoding Risk Minimization (LERM). It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label encodings. As a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a plugin. Theoretically, we analyze the relationships between LERM and ERM as well as EntMin. Empirically, we verify the superiority of the LERM under several label insufficient scenarios. The codes are available at https://github.com/zhangyl660/LERM.","url_abs":"https://arxiv.org/abs/2406.02862v1","url_pdf":"https://arxiv.org/pdf/2406.02862v1.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":"rethinking-guidance-information-to-utilize","repo_url":"https://github.com/zhangyl660/lerm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.02862","atlas_url":"https://app.syntology.ai/?focus=2406.02862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02862"}},"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":"deterministic:regex_extraction","url":"https://github.com/zhangyl660/LERM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangyl660/lerm","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":3,"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":14,"ran":12,"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":14,"samples":[{"code_sha256_prefix":"0372087a25c2c415","entry":"CDAN","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/loss.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0372087a25c2c415"}},{"code_sha256_prefix":"94b5622f0aa7add1","entry":"Entropy","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/loss.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94b5622f0aa7add1"}},{"code_sha256_prefix":"02d540d176585d46","entry":"LERM","repo":"zhangyl660/lerm","repo_kind":"official","path":"SSL/tllib/self_training/lerm.py","file_url":"https://github.com/zhangyl660/lerm/blob/HEAD/SSL/tllib/self_training/lerm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02d540d176585d46"}},{"code_sha256_prefix":"dbadbf1a0f7deaa6","entry":"alexnet","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/network.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dbadbf1a0f7deaa6"}},{"code_sha256_prefix":"9768efb52f591b55","entry":"grl_hook","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/loss.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9768efb52f591b55"}},{"code_sha256_prefix":"16f4eb1e884b4253","entry":"image_classification_test","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/train_image.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/train_image.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"16f4eb1e884b4253"}},{"code_sha256_prefix":"2cf9766f86cc3762","entry":"image_target","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/pre_process.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/pre_process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2cf9766f86cc3762"}},{"code_sha256_prefix":"f6d74b0470050306","entry":"image_test","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/pre_process.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/pre_process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6d74b0470050306"}},{"code_sha256_prefix":"782c9941712c32ae","entry":"image_train","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/pre_process.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/pre_process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"782c9941712c32ae"}},{"code_sha256_prefix":"693fef7015113684","entry":"inv_lr_scheduler","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/lr_schedule.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/lr_schedule.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"693fef7015113684"}},{"code_sha256_prefix":"edd7184ac144c4fa","entry":"l_loader","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/data_list.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/data_list.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"edd7184ac144c4fa"}},{"code_sha256_prefix":"2c5ce24ea2b5d2a4","entry":"rgb_loader","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/data_list.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/data_list.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c5ce24ea2b5d2a4"}},{"code_sha256_prefix":"e352afa5762c5a6b","entry":"calc_coeff","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/network.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/network.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e352afa5762c5a6b"}},{"code_sha256_prefix":"2301055cb33836bc","entry":"make_dataset","repo":"zhangyl660/LERM","repo_kind":"official","path":"UDA/DA/CDAN-LERM/data_list.py","file_url":"https://github.com/zhangyl660/LERM/blob/HEAD/UDA/DA/CDAN-LERM/data_list.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2301055cb33836bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}