{"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/reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","arxiv_id":"1909.11556","date":"2019-09-25","proceeding":"ICLR 2020 1","authors":["Angela Fan","Edouard Grave","Armand Joulin"],"abstract":"Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of parameters, necessitating a large amount of computation and making them prone to overfitting. In this work, we explore LayerDrop, a form of structured dropout, which has a regularization effect during training and allows for efficient pruning at inference time. In particular, we show that it is possible to select sub-networks of any depth from one large network without having to finetune them and with limited impact on performance. We demonstrate the effectiveness of our approach by improving the state of the art on machine translation, language modeling, summarization, question answering, and language understanding benchmarks. Moreover, we show that our approach leads to small BERT-like models of higher quality compared to training from scratch or using distillation.","url_abs":"https://arxiv.org/abs/1909.11556v1","url_pdf":"https://arxiv.org/pdf/1909.11556v1.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":"reducing-transformer-depth-on-demand-with-1","repo_url":"https://github.com/c00k1ez/plain-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reducing-transformer-depth-on-demand-with-1","repo_url":"https://github.com/prajjwal1/adaptive_transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reducing-transformer-depth-on-demand-with-1","repo_url":"https://github.com/prajjwal1/fluence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reducing-transformer-depth-on-demand-with-1","repo_url":"https://github.com/thunlp-mt/promptgating4mctg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"reducing-transformer-depth-on-demand-with-1","repo_url":"https://github.com/pytorch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"layerdrop","method_name":"LayerDrop"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"layerdrop","name":"LayerDrop","full_name":"LayerDrop"}],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-eli5","task":"Open-Domain Question Answering","dataset":"ELI5","model":"Transformer Multitask + LayerDrop","rank_in_archive_order":5,"of":6,"metrics":{"Rouge-1":"29.4","Rouge-2":"5.5","Rouge-L":"23.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1909.11556","atlas_url":"https://app.syntology.ai/?focus=1909.11556","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":"1909.11556"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1909.11556\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1909.11556"},"call":"get_concepts_for_paper(arxiv_id=\"1909.11556\")"}],"by_repo":[{"repo":"c00k1ez/plain-transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1908.04319","2004.08249"],"harvested_for_calls":[{"arxiv_id":"1908.04319","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1908.04319"},"call":"get_harvested_code_for_paper(arxiv_id=\"1908.04319\")"},{"arxiv_id":"2004.08249","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.08249"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.08249\")"}]},{"repo":"prajjwal1/adaptive_transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"prajjwal1/fluence","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.00015"],"harvested_for_calls":[{"arxiv_id":"1909.00015","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.00015"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.00015\")"}]},{"repo":"thunlp-mt/promptgating4mctg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.09387"],"harvested_for_calls":[{"arxiv_id":"2212.09387","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.09387"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.09387\")"}]},{"repo":"pytorch/fairseq","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2105.08206","2105.14850","2203.09163"],"harvested_for_calls":[{"arxiv_id":"2105.08206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.08206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.08206\")"},{"arxiv_id":"2105.14850","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14850"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14850\")"},{"arxiv_id":"2203.09163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09163\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"d71c96b75a17a999747ec8d75b536023aeba8b161d39e6b28f374acdaae15c7f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}