{"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/panda-prompt-transfer-meets-knowledge","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","arxiv_id":"2208.10160","date":"2022-08-22","proceeding":null,"authors":["Qihuang Zhong","Liang Ding","Juhua Liu","Bo Du","DaCheng Tao"],"abstract":"Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely PANDA) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) our proposed metric works well to predict the prompt transferability; 2) our PANDA consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes; 3) with our PANDA approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios. We have publicly released our code in https://github.com/WHU-ZQH/PANDA.","url_abs":"https://arxiv.org/abs/2208.10160v2","url_pdf":"https://arxiv.org/pdf/2208.10160v2.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":"panda-prompt-transfer-meets-knowledge","repo_url":"https://github.com/whu-zqh/panda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.10160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10160"}},"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/whu-zqh/panda","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"00b3090f89b698e1","entry":"build_relative_position","repo":"whu-zqh/panda","repo_kind":"official","path":"p-tuning-v2/model/deberta.py","file_url":"https://github.com/whu-zqh/panda/blob/HEAD/p-tuning-v2/model/deberta.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00b3090f89b698e1"}},{"code_sha256_prefix":"ea37553c09194184","entry":"c2p_dynamic_expand","repo":"whu-zqh/panda","repo_kind":"official","path":"p-tuning-v2/model/deberta.py","file_url":"https://github.com/whu-zqh/panda/blob/HEAD/p-tuning-v2/model/deberta.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea37553c09194184"}},{"code_sha256_prefix":"05732f1a5126672d","entry":"get_mask","repo":"whu-zqh/panda","repo_kind":"official","path":"p-tuning-v2/model/deberta.py","file_url":"https://github.com/whu-zqh/panda/blob/HEAD/p-tuning-v2/model/deberta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05732f1a5126672d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}