{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/achieving-forgetting-prevention-and-knowledge-1","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","arxiv_id":"2112.02706","date":"2021-12-05","proceeding":"NeurIPS 2021 12","authors":["Zixuan Ke","Bing Liu","Nianzu Ma","Hu Xu","Lei Shu"],"abstract":"Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques focus only on overcoming CF and have no mechanism to encourage KT, and thus do not do well in KT. Although several papers have tried to deal with both CF and KT, our experiments show that they suffer from serious CF when the tasks do not have much shared knowledge. Another observation is that most current CL methods do not use pre-trained models, but it has been shown that such models can significantly improve the end task performance. For example, in natural language processing, fine-tuning a BERT-like pre-trained language model is one of the most effective approaches. However, for CL, this approach suffers from serious CF. An interesting question is how to make the best use of pre-trained models for CL. This paper proposes a novel model called CTR to solve these problems. Our experimental results demonstrate the effectiveness of CTR","url_abs":"https://arxiv.org/abs/2112.02706v1","url_pdf":"https://arxiv.org/pdf/2112.02706v1.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":"achieving-forgetting-prevention-and-knowledge-1","repo_url":"https://github.com/zixuanke/pycontinual","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"20newsgroup-10-tasks","name":"20Newsgroup (10 tasks)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-20newsgroup-10-tasks","task":"Continual Learning","dataset":"20Newsgroup (10 tasks)","model":"CTR","rank_in_archive_order":1,"of":6,"metrics":{"F1 - macro":"0.9523"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","task":"Continual Learning","dataset":"ASC (19 tasks)","model":"Multi-task Learning (MTL; Upper Bound)","rank_in_archive_order":1,"of":15,"metrics":{"F1 - macro":"0.8811"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","task":"Continual Learning","dataset":"ASC (19 tasks)","model":"CTR","rank_in_archive_order":2,"of":15,"metrics":{"F1 - macro":"0.8362"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","task":"Continual Learning","dataset":"ASC (19 tasks)","model":"Independent Learning (ONE)","rank_in_archive_order":8,"of":15,"metrics":{"F1 - macro":"0.7807"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","task":"Continual Learning","dataset":"ASC (19 tasks)","model":"Naive Continual Learning (NCL)","rank_in_archive_order":10,"of":15,"metrics":{"F1 - macro":"0.7664"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-dsc-10-tasks","task":"Continual Learning","dataset":"DSC (10 tasks)","model":"CTR","rank_in_archive_order":1,"of":6,"metrics":{"F1 - macro":"0.8875"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.02706","atlas_url":"https://app.syntology.ai/?focus=2112.02706","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2112.02706"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.02706\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.02706"},"call":"get_concepts_for_paper(arxiv_id=\"2112.02706\")"}],"by_repo":[{"repo":"zixuanke/pycontinual","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cf195f7f840fdaaf602c763d6c460fc5c251379f4fc0d3bca9c2d6182f7a1350","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}