{"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/distill-the-best-ignore-the-rest-improving","title":"Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning","arxiv_id":"2411.12115","date":"2024-11-18","proceeding":null,"authors":["Brian B. Moser","Federico Raue","Tobias C. Nauen","Stanislav Frolov","Andreas Dengel"],"abstract":"Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel \"Prune First, Distill After\" framework that systematically prunes datasets via loss-based sampling prior to distillation. By leveraging pruning before classical distillation techniques and generative priors, we create a representative core-set that leads to enhanced generalization for unseen architectures - a significant challenge of current distillation methods. More specifically, our proposed framework significantly boosts distilled quality, achieving up to a 5.2 percentage points accuracy increase even with substantial dataset pruning, i.e., removing 80% of the original dataset prior to distillation. Overall, our experimental results highlight the advantages of our easy-sample prioritization and cross-architecture robustness, paving the way for more effective and high-quality dataset distillation.","url_abs":"https://arxiv.org/abs/2411.12115v1","url_pdf":"https://arxiv.org/pdf/2411.12115v1.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":"distill-the-best-ignore-the-rest-improving","repo_url":"https://github.com/Brian-Moser/prune_and_distill","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dataset-distillation","task_name":"Dataset Distillation"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.12115","atlas_url":"https://app.syntology.ai/?focus=2411.12115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12115"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Brian-Moser/prune_and_distill","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"8ac263b783faa918","entry":"build_dataset","repo":"Brian-Moser/prune_and_distill","repo_kind":"official","path":"src/glad_utils.py","file_url":"https://github.com/Brian-Moser/prune_and_distill/blob/HEAD/src/glad_utils.py","link_basis":"first_harvest_node","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":"8ac263b783faa918"}},{"code_sha256_prefix":"1851109ed71beae1","entry":"prepare_LDM_latents_encode","repo":"Brian-Moser/prune_and_distill","repo_kind":"official","path":"src/glad_utils.py","file_url":"https://github.com/Brian-Moser/prune_and_distill/blob/HEAD/src/glad_utils.py","link_basis":"first_harvest_node","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":"1851109ed71beae1"}},{"code_sha256_prefix":"b50ce4795030472c","entry":"prepare_LDM_latents_encode_compression","repo":"Brian-Moser/prune_and_distill","repo_kind":"official","path":"src/glad_utils.py","file_url":"https://github.com/Brian-Moser/prune_and_distill/blob/HEAD/src/glad_utils.py","link_basis":"first_harvest_node","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":"b50ce4795030472c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}