{"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/hyperspherical-variational-auto-encoders","title":"Hyperspherical Variational Auto-Encoders","arxiv_id":"1804.00891","date":"2018-04-03","proceeding":null,"authors":["Tim R. Davidson","Luca Falorsi","Nicola De Cao","Thomas Kipf","Jakub M. Tomczak"],"abstract":"The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or $\\mathcal{S}$-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, $\\mathcal{N}$-VAE, in low dimensions on other data types. Code at http://github.com/nicola-decao/s-vae-tf and https://github.com/nicola-decao/s-vae-pytorch","url_abs":"https://arxiv.org/abs/1804.00891v3","url_pdf":"https://arxiv.org/pdf/1804.00891v3.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":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/nicola-decao/s-vae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/nicola-decao/s-vae-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/nicola-decao/s-vae-tf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/Chenxingyu1990/gzsl_svae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/alexanderimanicowenrivers/Neural-Variational-Knowledge-Graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/clementchadebec/benchmark_VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hyperspherical-variational-auto-encoders","repo_url":"https://github.com/jiacheng-xu/vmf_vae_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-citeseer","task":"Link Prediction","dataset":"Citeseer","model":"S-VGAE","rank_in_archive_order":7,"of":13,"metrics":{"AP":"95.2","AUC":"94.7"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-cora","task":"Link Prediction","dataset":"Cora","model":"S-VGAE","rank_in_archive_order":6,"of":13,"metrics":{"AP":"94.1%","AUC":"94.1%"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-pubmed","task":"Link Prediction","dataset":"Pubmed","model":"S-VGAE","rank_in_archive_order":8,"of":13,"metrics":{"AP":"96.0%","AUC":"96.0%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00891"}},"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/clementchadebec/benchmark_VAE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicola-decao/s-vae-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexanderimanicowenrivers/Neural-Variational-Knowledge-Graphs","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicola-decao/s-vae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Chenxingyu1990/gzsl_svae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiacheng-xu/vmf_vae_nlp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicola-decao/s-vae-tf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":13,"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":"c6c94380b7037cdd","entry":"distribution_scale","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/util.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6c94380b7037cdd"}},{"code_sha256_prefix":"8bb8309107963c59","entry":"get_function","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/models/base.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/models/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bb8309107963c59"}},{"code_sha256_prefix":"4798b54bae1a0948","entry":"get_function","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/losses.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4798b54bae1a0948"}},{"code_sha256_prefix":"13d6783a3b02acab","entry":"hinge_loss","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/losses.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13d6783a3b02acab"}},{"code_sha256_prefix":"bf65b95c02161a27","entry":"ive","repo":"nicola-decao/s-vae","repo_kind":"official","path":"hyperspherical_vae/ops/ive.py","file_url":"https://github.com/nicola-decao/s-vae/blob/HEAD/hyperspherical_vae/ops/ive.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf65b95c02161a27"}},{"code_sha256_prefix":"965d80dff3c0ea12","entry":"logistic_loss","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/losses.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"965d80dff3c0ea12"}},{"code_sha256_prefix":"da8dad1ae4e89d2f","entry":"make_batches","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/util.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da8dad1ae4e89d2f"}},{"code_sha256_prefix":"d530125935cf01f4","entry":"negative_l1_distance","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/models/similarities.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/models/similarities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d530125935cf01f4"}},{"code_sha256_prefix":"d6b65c0c0f93913f","entry":"negative_l2_distance","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/models/similarities.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/models/similarities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6b65c0c0f93913f"}},{"code_sha256_prefix":"944cab66a4029ba0","entry":"negative_square_l2_distance","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/models/similarities.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/models/similarities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"944cab66a4029ba0"}},{"code_sha256_prefix":"85ce6b1b54f12b8c","entry":"read_triples","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/util.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85ce6b1b54f12b8c"}},{"code_sha256_prefix":"e7eeb0d9a6f27c68","entry":"renorm_unitvariance","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/constraints.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/constraints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7eeb0d9a6f27c68"}},{"code_sha256_prefix":"65360681d2699708","entry":"renorm_update_clip","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/constraints.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/constraints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65360681d2699708"}},{"code_sha256_prefix":"393991a5ea36fa36","entry":"renorm_update_var","repo":"acr42/Neural-Variational-Knowledge-Graphs","repo_kind":"listed","path":"vkge/training/constraints.py","file_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs/blob/HEAD/vkge/training/constraints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"393991a5ea36fa36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}