{"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/dataset-distillation","title":"Dataset Distillation","arxiv_id":"1811.10959","date":"2018-11-27","proceeding":null,"authors":["Tongzhou Wang","Jun-Yan Zhu","Antonio Torralba","Alexei A. Efros"],"abstract":"Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge from a large training dataset into a small one. The idea is to synthesize a small number of data points that do not need to come from the correct data distribution, but will, when given to the learning algorithm as training data, approximate the model trained on the original data. For example, we show that it is possible to compress 60,000 MNIST training images into just 10 synthetic distilled images (one per class) and achieve close to original performance with only a few gradient descent steps, given a fixed network initialization. We evaluate our method in various initialization settings and with different learning objectives. Experiments on multiple datasets show the advantage of our approach compared to alternative methods.","url_abs":"https://arxiv.org/abs/1811.10959v3","url_pdf":"https://arxiv.org/pdf/1811.10959v3.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":"dataset-distillation","repo_url":"https://github.com/SsnL/dataset-distillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dataset-distillation","repo_url":"https://github.com/Guang000/Awesome-Dataset-Distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dataset-distillation","repo_url":"https://github.com/liuyugeng/baadd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dataset-distillation","repo_url":"https://github.com/nus-hpc-ai-lab/dd-ranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dataset-distillation","repo_url":"https://github.com/showlab/data-centric.vlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dataset-distillation","repo_url":"https://github.com/showlab/datacentric.vlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dataset-distillation","task_name":"Dataset Distillation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10959"}},"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/Guang000/Awesome-Dataset-Distillation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SsnL/dataset-distillation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nus-hpc-ai-lab/dd-ranking","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/data-centric.vlp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuyugeng/baadd","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/datacentric.vlp","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"repositories":1},"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"c11329993135a3d9","entry":"default_augmentation","repo":"nus-hpc-ai-lab/dd-ranking","repo_kind":"listed","path":"ddranking/utils/train_and_eval.py","file_url":"https://github.com/nus-hpc-ai-lab/dd-ranking/blob/HEAD/ddranking/utils/train_and_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c11329993135a3d9"}},{"code_sha256_prefix":"5a60461e9e2f12d7","entry":"get_lr_scheduler","repo":"nus-hpc-ai-lab/dd-ranking","repo_kind":"listed","path":"ddranking/utils/train_and_eval.py","file_url":"https://github.com/nus-hpc-ai-lab/dd-ranking/blob/HEAD/ddranking/utils/train_and_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5a60461e9e2f12d7"}},{"code_sha256_prefix":"bacadd1761bd191c","entry":"get_optimizer","repo":"nus-hpc-ai-lab/dd-ranking","repo_kind":"listed","path":"ddranking/utils/train_and_eval.py","file_url":"https://github.com/nus-hpc-ai-lab/dd-ranking/blob/HEAD/ddranking/utils/train_and_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bacadd1761bd191c"}},{"code_sha256_prefix":"945f208c66022b60","entry":"average_train","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/baselines.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/baselines.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":"945f208c66022b60"}},{"code_sha256_prefix":"9ff25651ae35371b","entry":"clone_tuple","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"networks/utils.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/networks/utils.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":"9ff25651ae35371b"}},{"code_sha256_prefix":"2e1c63c03170fa89","entry":"configure","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/logging.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/logging.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":"2e1c63c03170fa89"}},{"code_sha256_prefix":"6ab4b45dcd11c1b3","entry":"final_objective_loss","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"basics.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/basics.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":"6ab4b45dcd11c1b3"}},{"code_sha256_prefix":"23ecd1ce493055e3","entry":"get_baseline_label_for_one_step","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/baselines.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/baselines.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":"23ecd1ce493055e3"}},{"code_sha256_prefix":"93fe1d69e4aca089","entry":"init_weights","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"networks/utils.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/networks/utils.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":"93fe1d69e4aca089"}},{"code_sha256_prefix":"062128c654a29276","entry":"load_results","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/io.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/io.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":"062128c654a29276"}},{"code_sha256_prefix":"12b94db554dfecb4","entry":"permute_list","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"train_distilled_image.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/train_distilled_image.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":"12b94db554dfecb4"}},{"code_sha256_prefix":"2103f67a4508d2cd","entry":"random_train","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/baselines.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/baselines.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":"2103f67a4508d2cd"}},{"code_sha256_prefix":"fdee81a9e734615a","entry":"read_bndbox","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"datasets/pascal_voc.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/datasets/pascal_voc.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":"fdee81a9e734615a"}},{"code_sha256_prefix":"26cdf3966b9542d6","entry":"read_split","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"datasets/pascal_voc.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/datasets/pascal_voc.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":"26cdf3966b9542d6"}},{"code_sha256_prefix":"2a1340040e1606e7","entry":"task_loss","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"basics.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/basics.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":"2a1340040e1606e7"}},{"code_sha256_prefix":"0250946399ff305f","entry":"to_np","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/io.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/io.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":"0250946399ff305f"}},{"code_sha256_prefix":"63eebd9902e8150b","entry":"to_torch","repo":"SsnL/dataset-distillation","repo_kind":"official","path":"utils/io.py","file_url":"https://github.com/SsnL/dataset-distillation/blob/HEAD/utils/io.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":"63eebd9902e8150b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}