Papers › Hyperspherical Variational Auto-Encoders

Hyperspherical Variational Auto-Encoders

3 Apr 2018arXiv:1804.00891archive 2025-07-28

Tim R. Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak

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 𝒮-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, 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

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1804.00891")

Code

Syntology Ran 0 of 14 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nicola-decao/s-vae officialmentioned in papermentioned on GitHubtfMIT report
nicola-decao/s-vae-pytorch officialmentioned in papermentioned on GitHubpytorchMIT report
nicola-decao/s-vae-tf officialmentioned in papermentioned on GitHubtfMIT report
Chenxingyu1990/gzsl_svae mentioned on GitHubpytorchMIT report
clementchadebec/benchmark_VAE mentioned on GitHubpytorch report
jiacheng-xu/vmf_vae_nlp mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 0 ran; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

14unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ive nicola-decao/s-vae/hyperspherical_vae/ops/ive.py official repository unverified MIT (permissive) · bf65b95c02161a27 · report
distribution_scale acr42/Neural-Variational-Knowledge-Graphs/vkge/training/util.py community (archive-listed) unverified MIT (permissive) · c6c94380b7037cdd · report
get_function acr42/Neural-Variational-Knowledge-Graphs/vkge/models/base.py community (archive-listed) unverified MIT (permissive) · 8bb8309107963c59 · report
get_function acr42/Neural-Variational-Knowledge-Graphs/vkge/training/losses.py community (archive-listed) unverified MIT (permissive) · 4798b54bae1a0948 · report
hinge_loss acr42/Neural-Variational-Knowledge-Graphs/vkge/training/losses.py community (archive-listed) unverified MIT (permissive) · 13d6783a3b02acab · report
logistic_loss acr42/Neural-Variational-Knowledge-Graphs/vkge/training/losses.py community (archive-listed) unverified MIT (permissive) · 965d80dff3c0ea12 · report
make_batches acr42/Neural-Variational-Knowledge-Graphs/vkge/training/util.py community (archive-listed) unverified MIT (permissive) · da8dad1ae4e89d2f · report
negative_l1_distance acr42/Neural-Variational-Knowledge-Graphs/vkge/models/similarities.py community (archive-listed) unverified MIT (permissive) · d530125935cf01f4 · report
negative_l2_distance acr42/Neural-Variational-Knowledge-Graphs/vkge/models/similarities.py community (archive-listed) unverified MIT (permissive) · d6b65c0c0f93913f · report
negative_square_l2_distance acr42/Neural-Variational-Knowledge-Graphs/vkge/models/similarities.py community (archive-listed) unverified MIT (permissive) · 944cab66a4029ba0 · report
read_triples acr42/Neural-Variational-Knowledge-Graphs/vkge/training/util.py community (archive-listed) unverified MIT (permissive) · 85ce6b1b54f12b8c · report
renorm_unitvariance acr42/Neural-Variational-Knowledge-Graphs/vkge/training/constraints.py community (archive-listed) unverified MIT (permissive) · e7eeb0d9a6f27c68 · report
renorm_update_clip acr42/Neural-Variational-Knowledge-Graphs/vkge/training/constraints.py community (archive-listed) unverified MIT (permissive) · 65360681d2699708 · report
renorm_update_var acr42/Neural-Variational-Knowledge-Graphs/vkge/training/constraints.py community (archive-listed) unverified MIT (permissive) · 393991a5ea36fa36 · report

Tasks

Link Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction Citeseer S-VGAE AP 95.2 #7 of 13 Archive leaderboard report
Link Prediction Citeseer S-VGAE AUC 94.7 #7 of 13 Archive leaderboard report
Link Prediction Cora S-VGAE AP 94.1% #6 of 13 Archive leaderboard report
Link Prediction Cora S-VGAE AUC 94.1% #6 of 13 Archive leaderboard report
Link Prediction Pubmed S-VGAE AP 96.0% #8 of 13 Archive leaderboard report
Link Prediction Pubmed S-VGAE AUC 96.0% #8 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections