Papers › A Transformer-based Framework for Multivariate Time Series Representation Learning

A Transformer-based Framework for Multivariate Time Series Representation Learning

6 Oct 2020arXiv:2010.02803archive 2025-07-28

George Zerveas, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty, Carsten Eickhoff

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and classification, forecasting and missing value imputation. By evaluating our models on several benchmark datasets for multivariate time series regression and classification, we show that not only does our modeling approach represent the most successful method employing unsupervised learning of multivariate time series presented to date, but also that it exceeds the current state-of-the-art performance of supervised methods; it does so even when the number of training samples is very limited, while offering computational efficiency. Finally, we demonstrate that unsupervised pre-training of our transformer models offers a substantial performance benefit over fully supervised learning, even without leveraging additional unlabeled data, i.e., by reusing the same data samples through the unsupervised objective.

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 32 code samples harvested from 3 repositories linked to this paper: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 16 ran (13 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 12 samples from 2 repositories, 7 ran (6 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gzerveas/mvts_transformer officialmentioned on GitHubpytorchMITSyntology: 20 samples, 16 ran (3 instrument-failed) · 4 unverified report
AntonioAcunzo/mvts_transformer mentioned on GitHubpytorchSyntology: not harvested report
appleparan/mise.py mentioned on GitHubpytorchMITSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
lizzylizzylizzy/evolvingattention mentioned on GitHubtfSyntology: not harvested report
pkuyym/evolvingattention mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
timeseriesAI/tsai pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Time Series is Worth 64 Words: Long-term Forecasting with Transformers (arXiv:2211.14730; that paper's own run record: 17 ran (of which 2 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

32 samples harvested: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
19ran
9unverified

Licence: 6 of the 32 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. 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.

gzerveas/mvts_transformer official repository 20 samples, 16 ran (3 instrument-failed) · 4 unverified
acc_top_k src/utils/analysis.py ran MIT (permissive) · 4f27929df483e1c4 · report fixture: signature predictions:ndarray/2/int, y_true:ndarray/1/int · returned ndarray · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/utils/analysis.py ran MIT (permissive) · 431078d6fcc08958 · report fixture: signature y_pred:ndarray/1/int, y_true:ndarray/1/int, excluded_labels:list/1/int · returned float64 · level recorded 2026-09-25
collate_superv src/datasets/dataset.py ran MIT (permissive) · 94120ad91132bf72 · report fixture: signature data:list/1/tuple, max_len:NoneType/0/? · returned tuple · level recorded 2026-09-25
compensate_masking src/datasets/dataset.py ran · our draft was wrong fingerprinted MIT (permissive) · 0c1e47b7a9f0bc5c · report fixture: signature X:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
convert_metrics_per_batch_to_per_sample src/running.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · f79cf1a40c083fee · report fixture: returned list · level recorded 2026-09-27
get_loss_module src/models/loss.py ran MIT (permissive) here; the stored copy is pointer only · 5346622dac785f32 · report fixture: signature config:dict/0/? · returned MaskedMSELoss · level recorded 2026-09-24
get_optimizer in 228 papers src/optimizers.py ran MIT (permissive) · 98a9799efb4a305c · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-25
interpolate_missing src/datasets/data.py ran · our draft was wrong MIT (permissive) · c43495731acfe20c · report fixture: signature y:Series/1/float · returned Series · level recorded 2026-09-24
l2_reg_loss in 7 papers src/models/loss.py ran MIT (permissive) here; the stored copy is pointer only · 96c6fa7dd49845b2 · report fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-24
load_config in 389 papers src/utils/utils.py ran MIT (permissive) · db289815c50136e9 · report fixture: signature config_filepath:str/0/str · returned dict · level recorded 2026-09-25
precision in 25 papers src/utils/analysis.py ran fingerprinted MIT (permissive) · 839af27815f6fa38 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, label:int/0/int · returned float64 · level recorded 2026-09-25
process_data in 61 papers src/datasets/utils.py ran MIT (permissive) · 51e3a59616ee190e · report fixture: signature X:DataFrame/0/?, min_len:int/0/int, normalise:str/0/str · returned ndarray · level recorded 2026-09-25
subsample in 25 papers src/datasets/data.py ran MIT (permissive) here; the stored copy is pointer only · 99cb2d7796fc399b · report fixture: signature y:Series/1/int, limit:int/0/int, factor:int/0/int · returned Series · level recorded 2026-09-24
timer in 24 papers src/utils/utils.py ran MIT (permissive) · 8269a8d00bc80c97 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
transduct_mask src/datasets/dataset.py ran MIT (permissive) · f77dc925dc416cc7 · report fixture: signature X:ndarray/2/float, mask_feats:list/1/int, start_hint:float/0/float, end_hint:float/0/float · returned ndarray · level recorded 2026-09-25
uniform_scaling src/datasets/utils.py ran fingerprinted MIT (permissive) · 6c254811cc3193b1 · report fixture: signature data:list/1/float, max_len:int/0/int · returned list · level recorded 2026-09-25
load_from_tsfile_to_dataframe src/datasets/utils.py unverified MIT (permissive) · f88f4ea73750eaa3 · report
load_model in 479 papers src/utils/utils.py unverified MIT (permissive) · 06f548c9975c99a4 · report
model_factory src/models/ts_transformer.py unverified MIT (permissive) · 131b5708bcdc85d1 · report
split_dataset in 65 papers src/datasets/datasplit.py unverified MIT (permissive) · 761d7abb12b095eb · report
appleparan/mise.py community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
load in 392 papers mise/data.py ran MIT (permissive) · f766b8a4595da2de · report fixture: signature datecol:list/1/int, filepath:str/0/str · returned DataFrame · level recorded 2026-09-24
load_imputed mise/data.py ran MIT (permissive) · e3c61c91b91a7e4e · report fixture: signature datecol:list/1/int, filepath:str/0/str · returned DataFrame · level recorded 2026-09-24
load_station mise/data.py ran MIT (permissive) · 622e8059e9d2a770 · report fixture: signature df:DataFrame/0/?, code:int/0/int · returned DataFrame · level recorded 2026-09-24
parse_key mise/utils.py ran MIT (permissive) · bf6fb185b4d4efb5 · report fixture: signature df:DataFrame/0/?, period:str/0/str · returned list · level recorded 2026-09-24
parse_ykey mise/utils.py ran MIT (permissive) · 068024601e1b87e3 · report fixture: signature idx:DatetimeIndex/1/datetime64[us] · returned str · level recorded 2026-09-24
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input
mise/dl/rnn_mul_lstnet_skip.py ran fingerprinted MIT (permissive) · 048af2894f1a47f8 · report fixture: signature _input:Tensor/2/float, beta:float/0/float · returned Tensor · level recorded 2026-09-24
dataset2svinput mise/dl/dt_xgboost.py unverified MIT (permissive) · c600f54d66a899c1 · report
mw_df mise/dl/dt_xgboost.py unverified MIT (permissive) · 935882a101552616 · report
parse_wkey mise/utils.py unverified MIT (permissive) · 8bbe4bc623baaf81 · report
sim_xgboost mise/dl/dt_xgboost.py unverified MIT (permissive) · f283f0737d07a747 · report
pkuyym/evolvingattention community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_pos_encoder EA_DC_Transformer/src/models/ea_dc_transformer.py ran · our draft was wrong no licence file found · pointer only · 578b29c746156148 · report fixture: signature pos_encoding:str/0/str · returned type · level recorded 2026-09-22
model_factory EA_DC_Transformer/src/models/ea_dc_transformer.py unverified no licence file found · pointer only · 1dac9a2dac1bfabb · report

Tasks

Computational EfficiencyGeneral ClassificationImputationRepresentation LearningTime SeriesTime Series AnalysisTime Series ClassificationTime Series RegressionUnsupervised Pre-trainingregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Classification Insectwingbeat TST Accuracy 0.687 #2 of 2 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