{"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/realistic-evaluation-of-deep-semi-supervised","title":"Realistic Evaluation of Deep Semi-Supervised Learning Algorithms","arxiv_id":"1804.09170","date":"2018-04-24","proceeding":"NeurIPS 2018 12","authors":["Avital Oliver","Augustus Odena","Colin Raffel","Ekin D. Cubuk","Ian J. Goodfellow"],"abstract":"Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and that performance can degrade substantially when the unlabeled dataset contains out-of-class examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.","url_abs":"https://arxiv.org/abs/1804.09170v4","url_pdf":"https://arxiv.org/pdf/1804.09170v4.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":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/brain-research/realistic-ssl-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/DavidKo3/semi_supervised_mean_teacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/layumi/SOTA-semi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/melkherj/puddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/perrying/realistic-ssl-evaluation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"realistic-evaluation-of-deep-semi-supervised","repo_url":"https://github.com/siit-vtt/ssl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09170"}},"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/melkherj/puddle","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siit-vtt/ssl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/brain-research/realistic-ssl-evaluation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DavidKo3/semi_supervised_mean_teacher","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/perrying/realistic-ssl-evaluation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/layumi/SOTA-semi","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_fixture":2,"unverified":11},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":14,"ran":3,"repositories":4}},"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":"9570e36a7f52ab5d","entry":"check_size","repo":"siit-vtt/semi-supervised-learning-pytorch","repo_kind":"listed","path":"loader_cifar_zca.py","file_url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch/blob/HEAD/loader_cifar_zca.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9570e36a7f52ab5d"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"siit-vtt/semi-supervised-learning-pytorch","repo_kind":"listed","path":"preresnet_sd_cifar.py","file_url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch/blob/HEAD/preresnet_sd_cifar.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"1f390b46a93ced80","entry":"get_zca_normalization_param","repo":"perrying/realistic-ssl-evaluation-pytorch","repo_kind":"listed","path":"build_dataset.py","file_url":"https://github.com/perrying/realistic-ssl-evaluation-pytorch/blob/HEAD/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f390b46a93ced80"}},{"code_sha256_prefix":"4c46154099e4d408","entry":"top_k","repo":"brain-research/realistic-ssl-evaluation","repo_kind":"official","path":"evaluate_model.py","file_url":"https://github.com/brain-research/realistic-ssl-evaluation/blob/HEAD/evaluate_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c46154099e4d408"}},{"code_sha256_prefix":"fefabd373ecadbc2","entry":"active_evaluate","repo":"melkherj/puddle","repo_kind":"listed","path":"puddle/active_evaluate.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/active_evaluate.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":"fefabd373ecadbc2"}},{"code_sha256_prefix":"436b1dc12d590080","entry":"bert_featurize","repo":"melkherj/puddle","repo_kind":"listed","path":"puddle/datasets/amazon_reviews_bert.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/datasets/amazon_reviews_bert.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":"436b1dc12d590080"}},{"code_sha256_prefix":"05c1950f5c932d08","entry":"binary_class_metrics","repo":"melkherj/puddle","repo_kind":"listed","path":"puddle/active_evaluate.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/active_evaluate.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":"05c1950f5c932d08"}},{"code_sha256_prefix":"20ec0d4caa9c361d","entry":"gcn","repo":"perrying/realistic-ssl-evaluation-pytorch","repo_kind":"listed","path":"build_dataset.py","file_url":"https://github.com/perrying/realistic-ssl-evaluation-pytorch/blob/HEAD/build_dataset.py","link_basis":"first_harvest_node","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":"20ec0d4caa9c361d"}},{"code_sha256_prefix":"b96d4224eb3255fa","entry":"horizontal_flip","repo":"siit-vtt/semi-supervised-learning-pytorch","repo_kind":"listed","path":"loader_cifar_zca.py","file_url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch/blob/HEAD/loader_cifar_zca.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":"b96d4224eb3255fa"}},{"code_sha256_prefix":"55f1499fcb95cc00","entry":"random_crop","repo":"siit-vtt/semi-supervised-learning-pytorch","repo_kind":"listed","path":"loader_cifar_zca.py","file_url":"https://github.com/siit-vtt/semi-supervised-learning-pytorch/blob/HEAD/loader_cifar_zca.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":"55f1499fcb95cc00"}},{"code_sha256_prefix":"4f47977b925bb5e5","entry":"run_experiment","repo":"melkherj/puddle","repo_kind":"listed","path":"puddle/active_evaluate.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/active_evaluate.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":"4f47977b925bb5e5"}},{"code_sha256_prefix":"d035fc4df55fe056","entry":"sklearn_binarize_by_percentile","repo":"melkherj/puddle","repo_kind":"listed","path":"puddle/datasets/sklearn_datasets.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/datasets/sklearn_datasets.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":"d035fc4df55fe056"}},{"code_sha256_prefix":"ae84d93c214dfa6a","entry":"train_mt","repo":"DavidKo3/semi_supervised_mean_teacher","repo_kind":"listed","path":"methods.py","file_url":"https://github.com/DavidKo3/semi_supervised_mean_teacher/blob/HEAD/methods.py","link_basis":"first_harvest_node","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":"ae84d93c214dfa6a"}},{"code_sha256_prefix":"2250115852053551","entry":"train_pi","repo":"DavidKo3/semi_supervised_mean_teacher","repo_kind":"listed","path":"methods.py","file_url":"https://github.com/DavidKo3/semi_supervised_mean_teacher/blob/HEAD/methods.py","link_basis":"first_harvest_node","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":"2250115852053551"}},{"code_sha256_prefix":"915404fc2dd8ffd9","entry":"train_sup","repo":"DavidKo3/semi_supervised_mean_teacher","repo_kind":"listed","path":"methods.py","file_url":"https://github.com/DavidKo3/semi_supervised_mean_teacher/blob/HEAD/methods.py","link_basis":"first_harvest_node","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":"915404fc2dd8ffd9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}