{"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/adversarially-regularized-autoencoders","title":"Adversarially Regularized Autoencoders","arxiv_id":"1706.04223","date":"2017-06-13","proceeding":null,"authors":["Jake Zhao","Yoon Kim","Kelly Zhang","Alexander M. Rush","Yann Lecun"],"abstract":"Deep latent variable models, trained using variational autoencoders or\ngenerative adversarial networks, are now a key technique for representation\nlearning of continuous structures. However, applying similar methods to\ndiscrete structures, such as text sequences or discretized images, has proven\nto be more challenging. In this work, we propose a flexible method for training\ndeep latent variable models of discrete structures. Our approach is based on\nthe recently-proposed Wasserstein autoencoder (WAE) which formalizes the\nadversarial autoencoder (AAE) as an optimal transport problem. We first extend\nthis framework to model discrete sequences, and then further explore different\nlearned priors targeting a controllable representation. This adversarially\nregularized autoencoder (ARAE) allows us to generate natural textual outputs as\nwell as perform manipulations in the latent space to induce change in the\noutput space. Finally we show that the latent representation can be trained to\nperform unaligned textual style transfer, giving improvements both in\nautomatic/human evaluation compared to existing methods.","url_abs":"http://arxiv.org/abs/1706.04223v3","url_pdf":"http://arxiv.org/pdf/1706.04223v3.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":"adversarially-regularized-autoencoders","repo_url":"https://github.com/jakezhaojb/ARAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarially-regularized-autoencoders","repo_url":"https://github.com/aboev/arae-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarially-regularized-autoencoders","repo_url":"https://github.com/awant/arae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarially-regularized-autoencoders","repo_url":"https://github.com/fangleai/Implicit-LVM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarially-regularized-autoencoders","repo_url":"https://github.com/lingofunk/lingofunk-transfer-style","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adversarially-regularized-autoencoders","repo_url":"https://github.com/maxdel/rmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.04223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.04223"}},"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/lingofunk/lingofunk-transfer-style","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awant/arae","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fangleai/Implicit-LVM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxdel/rmt","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakezhaojb/ARAE","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aboev/arae-tf","reach":{"status":"unanswered"}}],"summary":{"ran_violates":1,"ran_honours":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"1a66e1c4bac566fd","entry":"get_answer","repo":"lingofunk/lingofunk-transfer-style","repo_kind":"listed","path":"lingofunk_transfer_style/__main__.py","file_url":"https://github.com/lingofunk/lingofunk-transfer-style/blob/HEAD/lingofunk_transfer_style/__main__.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1a66e1c4bac566fd"}},{"code_sha256_prefix":"96a82519cf456d04","entry":"last_saved_epoch","repo":"lingofunk/lingofunk-transfer-style","repo_kind":"listed","path":"lingofunk_transfer_style/__main__.py","file_url":"https://github.com/lingofunk/lingofunk-transfer-style/blob/HEAD/lingofunk_transfer_style/__main__.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"96a82519cf456d04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}