{"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/the-evolved-transformer","title":"The Evolved Transformer","arxiv_id":"1901.11117","date":"2019-01-30","proceeding":null,"authors":["David R. So","Chen Liang","Quoc V. Le"],"abstract":"Recent works have highlighted the strength of the Transformer architecture on sequence tasks while, at the same time, neural architecture search (NAS) has begun to outperform human-designed models. Our goal is to apply NAS to search for a better alternative to the Transformer. We first construct a large search space inspired by the recent advances in feed-forward sequence models and then run evolutionary architecture search with warm starting by seeding our initial population with the Transformer. To directly search on the computationally expensive WMT 2014 English-German translation task, we develop the Progressive Dynamic Hurdles method, which allows us to dynamically allocate more resources to more promising candidate models. The architecture found in our experiments -- the Evolved Transformer -- demonstrates consistent improvement over the Transformer on four well-established language tasks: WMT 2014 English-German, WMT 2014 English-French, WMT 2014 English-Czech and LM1B. At a big model size, the Evolved Transformer establishes a new state-of-the-art BLEU score of 29.8 on WMT'14 English-German; at smaller sizes, it achieves the same quality as the original \"big\" Transformer with 37.6% less parameters and outperforms the Transformer by 0.7 BLEU at a mobile-friendly model size of 7M parameters.","url_abs":"https://arxiv.org/abs/1901.11117v4","url_pdf":"https://arxiv.org/pdf/1901.11117v4.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":"the-evolved-transformer","repo_url":"https://github.com/tensorflow/tensor2tensor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"the-evolved-transformer","repo_url":"https://github.com/moon23k/Transformer_Archs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-evolved-transformer","repo_url":"https://github.com/nazarov-yuriy/zh-ru-shared-task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"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":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"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":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"Evolved Transformer Big","rank_in_archive_order":17,"of":27,"metrics":{"PPL":"28.6"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-czech","task":"Machine Translation","dataset":"WMT2014 English-Czech","model":"Evolved Transformer Big","rank_in_archive_order":1,"of":2,"metrics":{"BLEU score":"28.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-czech","task":"Machine Translation","dataset":"WMT2014 English-Czech","model":"Evolved Transformer Base","rank_in_archive_order":2,"of":2,"metrics":{"BLEU score":"27.6"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Evolved Transformer Big","rank_in_archive_order":26,"of":57,"metrics":{"BLEU score":"41.3"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Evolved Transformer Base","rank_in_archive_order":29,"of":57,"metrics":{"BLEU score":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Evolved Transformer Big","rank_in_archive_order":16,"of":91,"metrics":{"BLEU score":"29.8","Number of Params":"218M","SacreBLEU":"29.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Evolved Transformer Base","rank_in_archive_order":46,"of":91,"metrics":{"BLEU score":"28.4","Hardware Burden":"2488G"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.11117","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}