Papers › SOM-VAE: Interpretable Discrete Representation Learning on Time Series

SOM-VAE: Interpretable Discrete Representation Learning on Time Series

6 Jun 2018ICLR 2019 5arXiv:1806.02199archive 2025-07-28

Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch

High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose a new representation learning framework building on ideas from interpretable discrete dimensionality reduction and deep generative modeling. This framework allows us to learn discrete representations of time series, which give rise to smooth and interpretable embeddings with superior clustering performance. We introduce a new way to overcome the non-differentiability in discrete representation learning and present a gradient-based version of the traditional self-organizing map algorithm that is more performant than the original. Furthermore, to allow for a probabilistic interpretation of our method, we integrate a Markov model in the representation space. This model uncovers the temporal transition structure, improves clustering performance even further and provides additional explanatory insights as well as a natural representation of uncertainty. We evaluate our model in terms of clustering performance and interpretability on static (Fashion-)MNIST data, a time series of linearly interpolated (Fashion-)MNIST images, a chaotic Lorenz attractor system with two macro states, as well as on a challenging real world medical time series application on the eICU data set. Our learned representations compare favorably with competitor methods and facilitate downstream tasks on the real world data.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 6 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ratschlab/SOM-VAE officialmentioned in papermentioned on GitHubtfMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
KurochkinAlexey/SOM-VAE mentioned on GitHubpytorchSyntology: not harvested report
ai-how/TIme-series-clustering mentioned on GitHubtfSyntology: not harvested report
alexwndm/state-detection-somvae mentioned on GitHubpytorchMITSyntology: not harvested report
shrra/minisom mentioned on GitHubSyntology: not harvested report
merchen911/SOM-VAE tfSyntology: not harvested 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

6 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
2unverified

Licence: 0 of the 6 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 ratschlab/SOM-VAE. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ratschlab/SOM-VAE official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
bias_variable in 24 papers som_vae/somvae_model.py ran MIT (permissive) · 217082b54273942a · report fixture: signature shape:tuple/1/int, name:str/0/str · returned ResourceVariable · level recorded 2026-09-25
compute_NMI som_vae/utils.py ran fingerprinted MIT (permissive) · 68aa8e556d801b92 · report fixture: signature cluster_assignments:list/1/int, class_assignments:list/1/int · returned float64 · level recorded 2026-09-25
compute_purity som_vae/utils.py ran fingerprinted MIT (permissive) · a0a609c5dc52a0e6 · report fixture: signature cluster_assignments:list/1/int, class_assignments:list/1/int · returned float · level recorded 2026-09-25
interpolate_arrays som_vae/utils.py ran MIT (permissive) · dcccd82a2000d983 · report fixture: signature arr1:ndarray/2/float, arr2:ndarray/2/float, num_steps:int/0/int, interpolation_length:float/0/float · returned ndarray · level recorded 2026-09-25
conv2d in 119 papers som_vae/somvae_model.py unverified MIT (permissive) · ed079f79e2399a16 · report
weight_variable in 29 papers som_vae/somvae_model.py unverified MIT (permissive) · 27a65c2665dbbd2d · report

Tasks

ClusteringDimensionality ReductionRepresentation LearningTime SeriesTime Series AnalysisTime Series Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Clustering eICU Collaborative Research Database SOM-VAE-prob NMI (physiology_24_hours) 0.0421 #1 of 3 Archive leaderboard report
Time Series Clustering eICU Collaborative Research Database SOM-VAE-prob NMI (physiology_6_hours) 0.0474 #1 of 3 Archive leaderboard report
Time Series Clustering eICU Collaborative Research Database SOM-VAE NMI (physiology_12_hours) 0.0444 #3 of 3 Archive leaderboard report
Time Series Clustering eICU Collaborative Research Database SOM-VAE NMI (physiology_24_hours) 0.0354 #3 of 3 Archive leaderboard report
Time Series Clustering eICU Collaborative Research Database SOM-VAE NMI (physiology_6_hours) 0.0407 #3 of 3 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.

Methods

Interpretability

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