{"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/data-free-knowledge-distillation-for-deep","title":"Data-Free Knowledge Distillation for Deep Neural Networks","arxiv_id":"1710.07535","date":"2017-10-19","proceeding":null,"authors":["Raphael Gontijo Lopes","Stefano Fenu","Thad Starner"],"abstract":"Recent advances in model compression have provided procedures for compressing\nlarge neural networks to a fraction of their original size while retaining most\nif not all of their accuracy. However, all of these approaches rely on access\nto the original training set, which might not always be possible if the network\nto be compressed was trained on a very large dataset, or on a dataset whose\nrelease poses privacy or safety concerns as may be the case for biometrics\ntasks. We present a method for data-free knowledge distillation, which is able\nto compress deep neural networks trained on large-scale datasets to a fraction\nof their size leveraging only some extra metadata to be provided with a\npretrained model release. We also explore different kinds of metadata that can\nbe used with our method, and discuss tradeoffs involved in using each of them.","url_abs":"http://arxiv.org/abs/1710.07535v2","url_pdf":"http://arxiv.org/pdf/1710.07535v2.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":"data-free-knowledge-distillation-for-deep","repo_url":"https://github.com/huawei-noah/DAFL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"data-free-knowledge-distillation-for-deep","repo_url":"https://github.com/huawei-noah/Data-Efficient-Model-Compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-free-knowledge-distillation","task_name":"Data-free Knowledge Distillation"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.07535","atlas_url":"https://app.syntology.ai/?focus=1710.07535","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}