{"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/continual-pre-training-mitigates-forgetting","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","arxiv_id":"2205.09357","date":"2022-05-19","proceeding":null,"authors":["Andrea Cossu","Tinne Tuytelaars","Antonio Carta","Lucia Passaro","Vincenzo Lomonaco","Davide Bacciu"],"abstract":"Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is rarely applied during continual learning. We formalize and investigate the characteristics of the continual pre-training scenario in both language and vision environments, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks. We show that continually pre-trained models are robust against catastrophic forgetting and we provide strong empirical evidence supporting the fact that self-supervised pre-training is more effective in retaining previous knowledge than supervised protocols. Code is provided at https://github.com/AndreaCossu/continual-pretraining-nlp-vision .","url_abs":"https://arxiv.org/abs/2205.09357v1","url_pdf":"https://arxiv.org/pdf/2205.09357v1.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":"continual-pre-training-mitigates-forgetting","repo_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continual-pretraining","task_name":"Continual Pretraining"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.09357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09357"}},"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/andreacossu/continual-pretraining-nlp-vision","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"4f1b09f46b03c233","entry":"add_colorbar","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"cka.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/cka.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":"4f1b09f46b03c233"}},{"code_sha256_prefix":"219b7aaf978adc4f","entry":"create_tokenizer","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.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":"219b7aaf978adc4f"}},{"code_sha256_prefix":"2ed8cd5f08e8e626","entry":"create_tokenizer_cl","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.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":"2ed8cd5f08e8e626"}},{"code_sha256_prefix":"249e014939153c23","entry":"mean_pooling","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"senteval.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/senteval.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":"249e014939153c23"}},{"code_sha256_prefix":"5a1f7cf9990b1ac9","entry":"mycollate","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"continual-pretraining-cv-unsupervised.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/continual-pretraining-cv-unsupervised.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":"5a1f7cf9990b1ac9"}},{"code_sha256_prefix":"c7fe1178d14f6de8","entry":"mycollate_mbatches","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"continual-pretraining-cv-unsupervised.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/continual-pretraining-cv-unsupervised.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":"c7fe1178d14f6de8"}},{"code_sha256_prefix":"c734372fb6ca5cba","entry":"remap_classes","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.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":"c734372fb6ca5cba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}