{"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/training-generative-reversible-networks","title":"Training Generative Reversible Networks","arxiv_id":"1806.01610","date":"2018-06-05","proceeding":null,"authors":["Robin Tibor Schirrmeister","Patryk Chrabąszcz","Frank Hutter","Tonio Ball"],"abstract":"Generative models with an encoding component such as autoencoders currently\nreceive great interest. However, training of autoencoders is typically\ncomplicated by the need to train a separate encoder and decoder model that have\nto be enforced to be reciprocal to each other. To overcome this problem,\nby-design reversible neural networks (RevNets) had been previously used as\ngenerative models either directly optimizing the likelihood of the data under\nthe model or using an adversarial approach on the generated data. Here, we\ninstead investigate their performance using an adversary on the latent space in\nthe adversarial autoencoder framework. We investigate the generative\nperformance of RevNets on the CelebA dataset, showing that generative RevNets\ncan generate coherent faces with similar quality as Variational Autoencoders.\nThis first attempt to use RevNets inside the adversarial autoencoder framework\nslightly underperformed relative to recent advanced generative models using an\nautoencoder component on CelebA, but this gap may diminish with further\noptimization of the training setup of generative RevNets. In addition to the\nexperiments on CelebA, we show a proof-of-principle experiment on the MNIST\ndataset suggesting that adversary-free trained RevNets can discover meaningful\nlatent dimensions without pre-specifying the number of dimensions of the latent\nsampling distribution. In summary, this study shows that RevNets can be\nemployed in different generative training settings.\n  Source code for this study is at\nhttps://github.com/robintibor/generative-reversible","url_abs":"http://arxiv.org/abs/1806.01610v4","url_pdf":"http://arxiv.org/pdf/1806.01610v4.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":"training-generative-reversible-networks","repo_url":"https://github.com/robintibor/generative-reversible","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"robintibor/generative-reversible","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":"ceb12fcd943a6a8d508a26f455dc37ca865d2422032e3b99681aeece1303d357","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}