{"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/what-is-dataset-distillation-learning","title":"What is Dataset Distillation Learning?","arxiv_id":"2406.04284","date":"2024-06-06","proceeding":null,"authors":["William Yang","Ye Zhu","Zhiwei Deng","Olga Russakovsky"],"abstract":"Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information from the original dataset. While distilled data can be used to train high performing models, little is understood about how the information is stored. In this study, we posit and answer three questions about the behavior, representativeness, and point-wise information content of distilled data. We reveal distilled data cannot serve as a substitute for real data during training outside the standard evaluation setting for dataset distillation. Additionally, the distillation process retains high task performance by compressing information related to the early training dynamics of real models. Finally, we provide an framework for interpreting distilled data and reveal that individual distilled data points contain meaningful semantic information. This investigation sheds light on the intricate nature of distilled data, providing a better understanding on how they can be effectively utilized.","url_abs":"https://arxiv.org/abs/2406.04284v2","url_pdf":"https://arxiv.org/pdf/2406.04284v2.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":"what-is-dataset-distillation-learning","repo_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dataset-distillation","task_name":"Dataset Distillation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04284"}},"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/princetonvisualai/What-is-Dataset-Distillation-Learning","reach":{"status":"ok"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":8,"samples":[{"code_sha256_prefix":"5e29b1ebcaea48b4","entry":"ResNet18BN_AP","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"networks.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/networks.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":"5e29b1ebcaea48b4"}},{"code_sha256_prefix":"f0905c1fdd06eba0","entry":"conv_block","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"networks.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/networks.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":"f0905c1fdd06eba0"}},{"code_sha256_prefix":"00410f25eb7b4820","entry":"conv_block_pool","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"networks.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/networks.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":"00410f25eb7b4820"}},{"code_sha256_prefix":"5d8e4eb7d28fab7a","entry":"count_params","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/model_utils.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":"5d8e4eb7d28fab7a"}},{"code_sha256_prefix":"b12b65b7d96e1063","entry":"get_images","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/data_utils.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":"b12b65b7d96e1063"}},{"code_sha256_prefix":"1ba04deabfd0a9a6","entry":"get_loops","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/model_utils.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":"1ba04deabfd0a9a6"}},{"code_sha256_prefix":"eaa888097d8e8aef","entry":"organize_dst","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/data_utils.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":"eaa888097d8e8aef"}},{"code_sha256_prefix":"523247b2836cf333","entry":"split_validation","repo":"princetonvisualai/What-is-Dataset-Distillation-Learning","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/princetonvisualai/What-is-Dataset-Distillation-Learning/blob/HEAD/data_utils.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":"523247b2836cf333"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}