{"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/one-size-does-not-fit-all-investigating","title":"One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks","arxiv_id":"2112.08159","date":"2021-12-15","proceeding":null,"authors":["Manuel Senge","Timour Igamberdiev","Ivan Habernal"],"abstract":"Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price. We know that stricter privacy guarantees in differentially-private stochastic gradient descent (DP-SGD) generally degrade model performance. However, previous research on the efficiency of DP-SGD in NLP is inconclusive or even counter-intuitive. In this short paper, we provide an extensive analysis of different privacy preserving strategies on seven downstream datasets in five different `typical' NLP tasks with varying complexity using modern neural models based on BERT and XtremeDistil architectures. We show that unlike standard non-private approaches to solving NLP tasks, where bigger is usually better, privacy-preserving strategies do not exhibit a winning pattern, and each task and privacy regime requires a special treatment to achieve adequate performance.","url_abs":"https://arxiv.org/abs/2112.08159v3","url_pdf":"https://arxiv.org/pdf/2112.08159v3.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":"one-size-does-not-fit-all-investigating","repo_url":"https://github.com/trusthlt/dp-across-nlp-tasks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.08159","atlas_url":"https://app.syntology.ai/?focus=2112.08159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08159"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/trusthlt/dp-across-nlp-tasks","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_honours":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"c8e199b09d57c824","entry":"categorical_accuracy","repo":"trusthlt/dp-across-nlp-tasks","repo_kind":"official","path":"NLPCode/natural_language_inference/utils.py","file_url":"https://github.com/trusthlt/dp-across-nlp-tasks/blob/HEAD/NLPCode/natural_language_inference/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8e199b09d57c824"}},{"code_sha256_prefix":"3e21e6589663b136","entry":"epoch_time","repo":"trusthlt/dp-across-nlp-tasks","repo_kind":"official","path":"NLPCode/named_entity_recognition/utils.py","file_url":"https://github.com/trusthlt/dp-across-nlp-tasks/blob/HEAD/NLPCode/named_entity_recognition/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e21e6589663b136"}},{"code_sha256_prefix":"b6e673e2fb74169b","entry":"get_acc_pre_rec_f1","repo":"trusthlt/dp-across-nlp-tasks","repo_kind":"official","path":"NLPCode/named_entity_recognition/utils.py","file_url":"https://github.com/trusthlt/dp-across-nlp-tasks/blob/HEAD/NLPCode/named_entity_recognition/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6e673e2fb74169b"}},{"code_sha256_prefix":"593b63e88677631d","entry":"take_no_pad","repo":"trusthlt/dp-across-nlp-tasks","repo_kind":"official","path":"NLPCode/named_entity_recognition/utils.py","file_url":"https://github.com/trusthlt/dp-across-nlp-tasks/blob/HEAD/NLPCode/named_entity_recognition/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"593b63e88677631d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}