{"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/fraternal-dropout","title":"Fraternal Dropout","arxiv_id":"1711.00066","date":"2017-10-31","proceeding":"ICLR 2018 1","authors":["Konrad Zolna","Devansh Arpit","Dendi Suhubdy","Yoshua Bengio"],"abstract":"Recurrent neural networks (RNNs) are important class of architectures among\nneural networks useful for language modeling and sequential prediction.\nHowever, optimizing RNNs is known to be harder compared to feed-forward neural\nnetworks. A number of techniques have been proposed in literature to address\nthis problem. In this paper we propose a simple technique called fraternal\ndropout that takes advantage of dropout to achieve this goal. Specifically, we\npropose to train two identical copies of an RNN (that share parameters) with\ndifferent dropout masks while minimizing the difference between their\n(pre-softmax) predictions. In this way our regularization encourages the\nrepresentations of RNNs to be invariant to dropout mask, thus being robust. We\nshow that our regularization term is upper bounded by the expectation-linear\ndropout objective which has been shown to address the gap due to the difference\nbetween the train and inference phases of dropout. We evaluate our model and\nachieve state-of-the-art results in sequence modeling tasks on two benchmark\ndatasets - Penn Treebank and Wikitext-2. We also show that our approach leads\nto performance improvement by a significant margin in image captioning\n(Microsoft COCO) and semi-supervised (CIFAR-10) tasks.","url_abs":"http://arxiv.org/abs/1711.00066v4","url_pdf":"http://arxiv.org/pdf/1711.00066v4.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":"fraternal-dropout","repo_url":"https://github.com/kondiz/fraternal-dropout","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fraternal-dropout","method_name":"Fraternal Dropout"}],"datasets_introduced":[],"methods_introduced":[{"slug":"fraternal-dropout","name":"Fraternal Dropout","full_name":"Fraternal Dropout"}],"results":[{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"AWD-LSTM 3-layer with Fraternal dropout","rank_in_archive_order":28,"of":43,"metrics":{"Params":"24M","Test perplexity":"56.8","Validation perplexity":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"AWD-LSTM 3-layer with Fraternal dropout","rank_in_archive_order":29,"of":38,"metrics":{"Number of params":"34M","Test perplexity":"64.1","Validation perplexity":"66.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.00066","atlas_url":"https://app.syntology.ai/?focus=1711.00066","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":"1711.00066"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.00066\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.00066"},"call":"get_concepts_for_paper(arxiv_id=\"1711.00066\")"}],"by_repo":[{"repo":"kondiz/fraternal-dropout","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"9fba2cc532e12689496eb0d88335c0c5e14a28cb681095161a2a28ed828a5eb6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}