{"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/fast-trainable-projection-for-robust-fine-1","title":"Fast Trainable Projection for Robust Fine-Tuning","arxiv_id":"2310.19182","date":"2023-10-29","proceeding":"NeurIPS 2023 11","authors":["Junjiao Tian","Yen-Cheng Liu","James Seale Smith","Zsolt Kira"],"abstract":"Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. Recently, projected gradient descent has been successfully used in robust fine-tuning by constraining the deviation from the initialization of the fine-tuned model explicitly through projection. However, algorithmically, two limitations prevent this method from being adopted more widely, scalability and efficiency. In this paper, we propose a new projection-based fine-tuning algorithm, Fast Trainable Projection (FTP) for computationally efficient learning of per-layer projection constraints, resulting in an average $35\\%$ speedup on our benchmarks compared to prior works. FTP can be combined with existing optimizers such as AdamW, and be used in a plug-and-play fashion. Finally, we show that FTP is a special instance of hyper-optimizers that tune the hyper-parameters of optimizers in a learnable manner through nested differentiation. Empirically, we show superior robustness on OOD datasets, including domain shifts and natural corruptions, across four different vision tasks with five different pre-trained models. Additionally, we demonstrate that FTP is broadly applicable and beneficial to other learning scenarios such as low-label and continual learning settings thanks to its easy adaptability. The code will be available at https://github.com/GT-RIPL/FTP.git.","url_abs":"https://arxiv.org/abs/2310.19182v1","url_pdf":"https://arxiv.org/pdf/2310.19182v1.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":"fast-trainable-projection-for-robust-fine-1","repo_url":"https://github.com/gt-ripl/ftp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fast-trainable-projection-for-robust-fine-1","repo_url":"https://github.com/chengyuehuang511/frames-vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.19182","atlas_url":"https://app.syntology.ai/?focus=2310.19182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19182"}},"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":"deterministic:regex_extraction","url":"https://github.com/GT-RIPL/FTP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengyuehuang511/frames-vqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gt-ripl/ftp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"2a80220dabcb742a","entry":"conv1x1","repo":"GT-RIPL/FTP","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/GT-RIPL/FTP/blob/HEAD/models/resnet.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":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"GT-RIPL/FTP","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/GT-RIPL/FTP/blob/HEAD/models/resnet.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":"600ff2c45e0de056"}},{"code_sha256_prefix":"b3795a1e9dca08a8","entry":"FTP","repo":"chengyuehuang511/frames-vqa","repo_kind":"listed","path":"optimizer/ftp.py","file_url":"https://github.com/chengyuehuang511/frames-vqa/blob/HEAD/optimizer/ftp.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":"b3795a1e9dca08a8"}},{"code_sha256_prefix":"1f63157bc6a0bb4a","entry":"resnet18","repo":"GT-RIPL/FTP","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/GT-RIPL/FTP/blob/HEAD/models/resnet.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":"1f63157bc6a0bb4a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}