{"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/towards-a-general-framework-for-continual","title":"Towards a General Framework for Continual Learning with Pre-training","arxiv_id":"2310.13888","date":"2023-10-21","proceeding":null,"authors":["Liyuan Wang","Jingyi Xie","Xingxing Zhang","Hang Su","Jun Zhu"],"abstract":"In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world dynamics. From a theoretical perspective, we decompose its objective into three hierarchical components, including within-task prediction, task-identity inference, and task-adaptive prediction. Then we propose an innovative approach to explicitly optimize these components with parameter-efficient fine-tuning (PEFT) techniques and representation statistics. We empirically demonstrate the superiority and generality of our approach in downstream continual learning, and further explore the applicability of PEFT techniques in upstream continual learning. We also discuss the biological basis of the proposed framework with recent advances in neuroscience.","url_abs":"https://arxiv.org/abs/2310.13888v2","url_pdf":"https://arxiv.org/pdf/2310.13888v2.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":"towards-a-general-framework-for-continual","repo_url":"https://github.com/thu-ml/hide-prompt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.13888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13888"}},"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/thu-ml/HiDe-Prompt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thu-ml/hide-prompt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"a2575f11d9ebef0c","entry":"EPrompt","repo":"thu-ml/hide-prompt","repo_kind":"official","path":"peft/prompt/hide_prompt.py","file_url":"https://github.com/thu-ml/hide-prompt/blob/HEAD/peft/prompt/hide_prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2575f11d9ebef0c"}},{"code_sha256_prefix":"ee95af3ec5c38df5","entry":"checkpoint_filter_fn","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"vits/hide_prompt_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_prompt_vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee95af3ec5c38df5"}},{"code_sha256_prefix":"14b5572abcfb8ffd","entry":"get_episode_dataset","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"few_shot_datasets.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/few_shot_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14b5572abcfb8ffd"}},{"code_sha256_prefix":"6c600a2f0f2361f1","entry":"get_init_weights_vit","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"vits/hide_prompt_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_prompt_vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"code_sha256_prefix":"d2462a444e3fa1df","entry":"get_init_weights_vit","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"vits/hide_lora_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_lora_vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2462a444e3fa1df"}},{"code_sha256_prefix":"d43a8b4e6947732e","entry":"get_query_dataset","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"few_shot_datasets.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/few_shot_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d43a8b4e6947732e"}},{"code_sha256_prefix":"a6e17b60ed761713","entry":"resize_pos_embed","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"vits/hide_prompt_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_prompt_vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6e17b60ed761713"}},{"code_sha256_prefix":"265ea374aab10001","entry":"target_transform","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"265ea374aab10001"}},{"code_sha256_prefix":"f8e1687c33938e06","entry":"get_dataset","repo":"thu-ml/HiDe-Prompt","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/datasets.py","link_basis":"harvester_set","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":"f8e1687c33938e06"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}