Papers › Considering Nonstationary within Multivariate Time Series with Variational...

Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting

8 Mar 2024arXiv:2403.05406archive 2025-07-28

Muyao Wang, Wenchao Chen, Bo Chen

The forecasting of Multivariate Time Series (MTS) has long been an important but challenging task. Due to the non-stationary problem across long-distance time steps, previous studies primarily adopt stationarization method to attenuate the non-stationary problem of the original series for better predictability. However, existing methods always adopt the stationarized series, which ignores the inherent non-stationarity, and has difficulty in modeling MTS with complex distributions due to the lack of stochasticity. To tackle these problems, we first develop a powerful hierarchical probabilistic generative module to consider the non-stationarity and stochastic characteristics within MTS, and then combine it with transformer for a well-defined variational generative dynamic model named Hierarchical Time series Variational Transformer (HTV-Trans), which recovers the intrinsic non-stationary information into temporal dependencies. Being a powerful probabilistic model, HTV-Trans is utilized to learn expressive representations of MTS and applied to forecasting tasks. Extensive experiments on diverse datasets show the efficiency of HTV-Trans on MTS forecasting tasks

PaperPDFCodeCode Syntology ranMethod as code

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 17 code samples harvested from 1 repository linked to this paper: 12 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 17 samples from 1 repository, 12 ran (12 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

flare200020/HTV_Trans officialpytorchSyntology: 17 samples, 12 ran (0 instrument-failed) · 5 unverified 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

17 samples harvested: 12 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

12ran
5unverified

Licence: 17 of the 17 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 flare200020/HTV_Trans. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

flare200020/HTV_Trans official repository 17 samples, 12 ran (0 instrument-failed) · 5 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
HTV-Trans/models.py ran no licence file found · pointer only · d8b17088c30d7c1f · report fixture: returned Attention · level recorded 2026-09-22
Conv1D in 9 papers HTV-Trans/models.py ran no licence file found · pointer only · 74b3323d27fe93b1 · report fixture: returned Conv1D · level recorded 2026-09-22
DataEmbedding in 9 papers HTV-Trans/models.py ran no licence file found · pointer only · a3fa5fe34f49177a · report fixture: returned DataEmbedding · level recorded 2026-09-22
HTPGM HTV-Trans/models.py ran no licence file found · pointer only · 68581577d956b157 · report fixture: returned HTPGM · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
HTV-Trans/models.py ran no licence file found · pointer only · a6928a70b80bc1b4 · report fixture: returned LayerNorm · level recorded 2026-09-22
LinearUnit HTV-Trans/models.py ran no licence file found · pointer only · 46fcae58fc9b08c8 · report fixture: returned LinearUnit · level recorded 2026-09-22
LossFunctions HTV-Trans/models.py ran fingerprinted no licence file found · pointer only · faaf5aa3e1f58182 · report fixture: signature x:Tensor/2/float, mu:Tensor/2/float, var:Tensor/2/float · returned Tensor · level recorded 2026-09-24
MLP in 375 papers HTV-Trans/models.py ran no licence file found · pointer only · 91d587405b55b923 · report fixture: returned MLP · level recorded 2026-09-22
Pooling in 6 papers HTV-Trans/models.py ran fingerprinted no licence file found · pointer only · 61bb2690669d49ba · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RevIN in 13 papers HTV-Trans/models.py ran no licence file found · pointer only · fc3c43db0c27518d · report fixture: returned RevIN · level recorded 2026-09-22
generate_Layer HTV-Trans/models.py ran no licence file found · pointer only · 9a7017403cb38629 · report fixture: returned generate_Layer · level recorded 2026-09-22
inference_Layer HTV-Trans/models.py ran no licence file found · pointer only · e529c294c27ea7ff · report fixture: returned inference_Layer · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
HTV-Trans/models.py unverified no licence file found · pointer only · 8783aa1a77c47581 · report
CombineNet HTV-Trans/models.py unverified no licence file found · pointer only · 0aae1d08b0d3b256 · report
SelfDefinedTransformer HTV-Trans/models.py unverified no licence file found · pointer only · ee1df127ca37104c · report
StackedVAGT HTV-Trans/models.py unverified no licence file found · pointer only · cc4dcb8be0047b03 · report
VariationalTransformer HTV-Trans/models.py unverified no licence file found · pointer only · 83ad7f4ae48a0064 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Hierarchical Time series Variational Transformer (HTV-Trans) (graph method: Hierarchical Time series Variational Transformer (HTV-Trans)). 20 bricks; individually on a fixture: 15 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. StackedVAGT entry · level 0 · unverified · cc4dcb8be0047b03
  2. CombineNet model · level 0 · unverified · 0aae1d08b0d3b256
  3. DataEmbedding helper · level 1 · ran · a3fa5fe34f49177a
  4. LinearUnit helper · level 1 · ran · 46fcae58fc9b08c8
  5. LossFunctions loss · level 1 · ran · faaf5aa3e1f58182
  6. RevIN helper · level 1 · ran · fc3c43db0c27518d
  7. HTPGM model · level 1 · ran · 68581577d956b157
  8. VariationalTransformer model · level 0 · unverified · 83ad7f4ae48a0064
  9. PositionalEmbedding helper · level 1 · ran · 5da1d16a64cf53ce
  10. TimeFeatureEmbedding helper · level 1 · ran · 98a0817e251d19c7
  11. TokenEmbedding helper · level 1 · ran · 588a4a8475ed63a0
  12. generate_Layer helper · level 1 · ran · 9a7017403cb38629
  13. inference_Layer helper · level 1 · ran · e529c294c27ea7ff
  14. SelfDefinedTransformer model · level 0 · unverified · ee1df127ca37104c
  15. Block helper · level 0 · unverified · 8783aa1a77c47581
  16. Attention helper · level 1 · ran · d8b17088c30d7c1f
  17. LayerNorm helper · level 1 · ran · a6928a70b80bc1b4
  18. MLP helper · level 1 · ran · 91d587405b55b923
  19. Conv1D helper · level 1 · ran · 74b3323d27fe93b1
  20. Pooling helper · level 1 · ran · 61bb2690669d49ba

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2403.05406") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Time Series

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMTSMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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