{"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/efficient-contrastive-learning-via-novel-data","title":"Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning","arxiv_id":"2109.05941","date":"2021-09-10","proceeding":"EMNLP 2021 11","authors":["Seonghyeon Ye","Jiseon Kim","Alice Oh"],"abstract":"We introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation sequentially: cutoff and PCA jittering. While pretraining steps proceed, we apply curriculum learning by incrementing the augmentation degree for each difficulty step. After data augmentation is finished, contrastive learning is applied on projected embeddings of original and augmented examples. When finetuned on GLUE benchmark, our model outperforms baseline models, especially for sentence-level tasks. Additionally, this improvement is capable with only 70% of computational memory compared to the baseline model.","url_abs":"https://arxiv.org/abs/2109.05941v2","url_pdf":"https://arxiv.org/pdf/2109.05941v2.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":"efficient-contrastive-learning-via-novel-data","repo_url":"https://github.com/vano1205/efficientcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-pretraining","task_name":"Continual Pretraining"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.05941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05941"}},"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/vano1205/efficientcl","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"33c94929830b31c9","entry":"random_deletion","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33c94929830b31c9"}},{"code_sha256_prefix":"85f4d7cd22f3b8de","entry":"random_swap","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"85f4d7cd22f3b8de"}},{"code_sha256_prefix":"aa17b95c9417dad0","entry":"swap_word","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa17b95c9417dad0"}},{"code_sha256_prefix":"f15d53d3391db0a4","entry":"add_word","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"f15d53d3391db0a4"}},{"code_sha256_prefix":"315a874427b8d6e3","entry":"eda","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"315a874427b8d6e3"}},{"code_sha256_prefix":"6d5faa1643cd229d","entry":"get_only_chars","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"6d5faa1643cd229d"}},{"code_sha256_prefix":"461078e5a822e755","entry":"get_synonyms","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"461078e5a822e755"}},{"code_sha256_prefix":"96e275bc8e02d4d3","entry":"random_insertion","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"96e275bc8e02d4d3"}},{"code_sha256_prefix":"a8ed7ca8d981f8d2","entry":"synonym_replacement","repo":"vano1205/efficientcl","repo_kind":"official","path":"efficientcl/common/augmentation.py","file_url":"https://github.com/vano1205/efficientcl/blob/HEAD/efficientcl/common/augmentation.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":"a8ed7ca8d981f8d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}