{"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/fine-tuning-pre-trained-language-models","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","arxiv_id":"2211.01642","date":"2022-11-03","proceeding":null,"authors":["Haojie Zhang","Ge Li","Jia Li","Zhongjin Zhang","Yuqi Zhu","Zhi Jin"],"abstract":"Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we propose a Dynamic Parameter Selection (DPS) algorithm for the large-scale pre-trained models during fine-tuning, which adaptively selects a more promising subnetwork to perform staging updates based on gradients of back-propagation. Experiments on the GLUE benchmark show that DPS outperforms previous fine-tuning methods in terms of overall performance and stability, and consistently achieves better results with variable pre-trained language models. In addition, DPS brings a large magnitude of improvement in out-of-domain transferring experiments and low-resource scenarios, which shows that it can maintain stable general contextual features and reduce the representation collapse. We release our code at https://github.com/ZhangHaojie077/DPS","url_abs":"https://arxiv.org/abs/2211.01642v1","url_pdf":"https://arxiv.org/pdf/2211.01642v1.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":"fine-tuning-pre-trained-language-models","repo_url":"https://github.com/zhanghaojie077/dps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.01642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01642"}},"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":"deterministic:regex_extraction","url":"https://github.com/ZhangHaojie077/DPS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhanghaojie077/dps","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"6dc2be3dcd179daf","entry":"DPSDense","repo":"zhanghaojie077/dps","repo_kind":"official","path":"transformers/DPSDense/moudle.py","file_url":"https://github.com/zhanghaojie077/dps/blob/HEAD/transformers/DPSDense/moudle.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6dc2be3dcd179daf"}},{"code_sha256_prefix":"cc085a876a8faad0","entry":"grads_ops","repo":"zhanghaojie077/dps","repo_kind":"official","path":"transformers/DPSDense/grads_ops.py","file_url":"https://github.com/zhanghaojie077/dps/blob/HEAD/transformers/DPSDense/grads_ops.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc085a876a8faad0"}},{"code_sha256_prefix":"db2632aaaf76ff8e","entry":"grads_ops","repo":"zhanghaojie077/dps","repo_kind":"official","path":"transformers/DPSDense/moudle.py","file_url":"https://github.com/zhanghaojie077/dps/blob/HEAD/transformers/DPSDense/moudle.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"db2632aaaf76ff8e"}},{"code_sha256_prefix":"3322371b4a0a62ab","entry":"Grads_Ops","repo":"zhanghaojie077/dps","repo_kind":"official","path":"transformers/DPSDense/moudle.py","file_url":"https://github.com/zhanghaojie077/dps/blob/HEAD/transformers/DPSDense/moudle.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":"3322371b4a0a62ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}