{"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/self-adaptive-training-beyond-empirical-risk","title":"Self-Adaptive Training: beyond Empirical Risk Minimization","arxiv_id":"2002.10319","date":"2020-02-24","proceeding":"NeurIPS 2020 12","authors":["Lang Huang","Chao Zhang","Hongyang Zhang"],"abstract":"We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially corrupted training data. This problem is crucial towards robustly learning from data that are corrupted by, e.g., label noises and out-of-distribution samples. The standard empirical risk minimization (ERM) for such data, however, may easily overfit noises and thus suffers from sub-optimal performance. In this paper, we observe that model predictions can substantially benefit the training process: self-adaptive training significantly improves generalization over ERM under various levels of noises, and mitigates the overfitting issue in both natural and adversarial training. We evaluate the error-capacity curve of self-adaptive training: the test error is monotonously decreasing w.r.t. model capacity. This is in sharp contrast to the recently-discovered double-descent phenomenon in ERM which might be a result of overfitting of noises. Experiments on CIFAR and ImageNet datasets verify the effectiveness of our approach in two applications: classification with label noise and selective classification. We release our code at https://github.com/LayneH/self-adaptive-training.","url_abs":"https://arxiv.org/abs/2002.10319v2","url_pdf":"https://arxiv.org/pdf/2002.10319v2.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":"self-adaptive-training-beyond-empirical-risk","repo_url":"https://github.com/LayneH/self-adaptive-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-adaptive-training-beyond-empirical-risk","repo_url":"https://github.com/BorealisAI/towards-better-sel-cls","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-adaptive-training-beyond-empirical-risk","repo_url":"https://github.com/LayneH/SAT-selective-cls","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"self-adaptive-training-beyond-empirical-risk","repo_url":"https://github.com/MarinePICOT/Adversarial-Robustness-via-Fisher-Rao-Regularization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"self-adaptive-training","method_name":"Self-adaptive Training"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[{"slug":"self-adaptive-training","name":"Self-adaptive Training","full_name":"Self-adaptive Training"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.10319","atlas_url":"https://app.syntology.ai/?focus=2002.10319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10319"}},"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/LayneH/self-adaptive-training","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LayneH/SAT-selective-cls","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MarinePICOT/Adversarial-Robustness-via-Fisher-Rao-Regularization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BorealisAI/towards-better-sel-cls","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"cb4ce68cc060e246","entry":"SelfAdaptiveTrainingCE","repo":"LayneH/self-adaptive-training","repo_kind":"official","path":"losses/loss.py","file_url":"https://github.com/LayneH/self-adaptive-training/blob/HEAD/losses/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb4ce68cc060e246"}},{"code_sha256_prefix":"b47c02d80eb5a7e7","entry":"SelfAdativeTraining","repo":"BorealisAI/towards-better-sel-cls","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/BorealisAI/towards-better-sel-cls/blob/HEAD/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b47c02d80eb5a7e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}