{"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/mixed-curvature-variational-autoencoders-1","title":"Mixed-curvature Variational Autoencoders","arxiv_id":"1911.08411","date":"2019-11-19","proceeding":"ICLR 2020 1","authors":["Ondrej Skopek","Octavian-Eugen Ganea","Gary Bécigneul"],"abstract":"Euclidean geometry has historically been the typical \"workhorse\" for machine learning applications due to its power and simplicity. However, it has recently been shown that geometric spaces with constant non-zero curvature improve representations and performance on a variety of data types and downstream tasks. Consequently, generative models like Variational Autoencoders (VAEs) have been successfully generalized to elliptical and hyperbolic latent spaces. While these approaches work well on data with particular kinds of biases e.g. tree-like data for a hyperbolic VAE, there exists no generic approach unifying and leveraging all three models. We develop a Mixed-curvature Variational Autoencoder, an efficient way to train a VAE whose latent space is a product of constant curvature Riemannian manifolds, where the per-component curvature is fixed or learnable. This generalizes the Euclidean VAE to curved latent spaces and recovers it when curvatures of all latent space components go to 0.","url_abs":"https://arxiv.org/abs/1911.08411v2","url_pdf":"https://arxiv.org/pdf/1911.08411v2.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":"mixed-curvature-variational-autoencoders-1","repo_url":"https://github.com/oskopek/mvae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.08411","atlas_url":"https://app.syntology.ai/?focus=1911.08411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08411"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/oskopek/mvae","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"e1fe823ad0ece20a","entry":"all_models","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/all_models.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/all_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e1fe823ad0ece20a"}},{"code_sha256_prefix":"7a3010c14a89f246","entry":"canonical_name","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/all_models.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/all_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a3010c14a89f246"}},{"code_sha256_prefix":"360bfcf03cfbec8a","entry":"cdf_r","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/distributions/hyperbolic_radius.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/distributions/hyperbolic_radius.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"360bfcf03cfbec8a"}},{"code_sha256_prefix":"81544b61f125ae3d","entry":"diff","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/distributions/ars.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/distributions/ars.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81544b61f125ae3d"}},{"code_sha256_prefix":"c7ec5f7b40878d0f","entry":"grad_cdf_value_scale","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/distributions/hyperbolic_radius.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/distributions/hyperbolic_radius.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7ec5f7b40878d0f"}},{"code_sha256_prefix":"e89a04d86cc8eb8f","entry":"log_sum_exp_signs","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/distributions/pvae_utils.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/distributions/pvae_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e89a04d86cc8eb8f"}},{"code_sha256_prefix":"5a61d0a71b89572c","entry":"parse_component_str","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/utils.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a61d0a71b89572c"}},{"code_sha256_prefix":"f09eaf2b8361cf4b","entry":"rexpand","repo":"oskopek/mvae","repo_kind":"official","path":"mt/mvae/distributions/pvae_utils.py","file_url":"https://github.com/oskopek/mvae/blob/HEAD/mt/mvae/distributions/pvae_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f09eaf2b8361cf4b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}