Papers › Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

19 Dec 2019arXiv:1912.09363archive 2025-07-28

Bryan Lim, Sercan O. Arik, Nicolas Loeff, Tomas Pfister

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target. While several deep learning models have been proposed for multi-step prediction, they typically comprise black-box models which do not account for the full range of inputs present in common scenarios. In this paper, we introduce the Temporal Fusion Transformer (TFT) -- a novel attention-based architecture which combines high-performance multi-horizon forecasting with interpretable insights into temporal dynamics. To learn temporal relationships at different scales, the TFT utilizes recurrent layers for local processing and interpretable self-attention layers for learning long-term dependencies. The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes. On a variety of real-world datasets, we demonstrate significant performance improvements over existing benchmarks, and showcase three practical interpretability use-cases of TFT.

PaperPDFCodeCode 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 10 code samples harvested from 4 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 4 repositories, 8 ran (4 with no instrument failure; 4 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 8 of its repositories that Syntology harvested for other papers:

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.

36 repositories listed; official and paper-mentioned ones first.

AWarno/CancerOptimization mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
IKKIM00/multi-horizon-forecasting-comparison-between-TFT-and-DL-methods mentioned on GitHubpytorchSyntology: not harvested report
IKKIM00/stock_and_pm2.5_prediction_using_TFT mentioned on GitHubSyntology: not harvested report
JonathanRayner/Kaggle-Predict-Sales mentioned on GitHubSyntology: not harvested report
KalleBylin/temporal-fusion-transformers mentioned on GitHubSyntology: not harvested report
KalleBylin/tft_webapp mentioned on GitHubpytorchSyntology: not harvested report
LeeSH825/TemporalFusionTransformer mentioned on GitHubSyntology: not harvested report
LiamMaclean216/Any-Coin-TFN mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
LiamMaclean216/Temporal-Fusion-Transformer mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
MarigoldJ/TFT_application mentioned on GitHubSyntology: not harvested report
PlaytikaResearch/tft-torch mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
Scallions/tft_paddle mentioned on GitHubpaddleSyntology: not harvested report
Yoontae6719/Energy_project mentioned on GitHubpytorchMITSyntology: not harvested report
aqua1907/tft mentioned on GitHubSyntology: not harvested report
ashi-k/tft mentioned on GitHubtfSyntology: not harvested report
ashishKAgg/tft mentioned on GitHubtfSyntology: not harvested report
bobbercheng/ventilator-pressure-prediction mentioned on GitHubtfSyntology: not harvested report
damu4/tft-forecast mentioned on GitHubSyntology: not harvested report
dehoyosb/temporal_fusion_transformer_pytorch mentioned on GitHubpytorchSyntology: not harvested report
eeci/annex_37 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting (arXiv:2201.12886; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
ggaggu/Diprunning_study mentioned on GitHubSyntology: not harvested report
google-research/google-research mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
greatwhiz/tft_tf2 mentioned on GitHubtfSyntology: not harvested report
henghamao/tft mentioned on GitHubSyntology: not harvested report
jdb78/pytorch-forecasting mentioned on GitHubpytorchMITSyntology: not harvested report
mattsherar/Temporal_Fusion_Transform mentioned on GitHubpytorchSyntology: not harvested report
mavarick/tft mentioned on GitHubpytorchSyntology: not harvested report
mlverse/tft mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ntubiolin/tft mentioned on GitHubtfSyntology: not harvested report
stevinc/Transformer_Timeseries mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
unit8co/darts mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long-term Forecasting with TiDE: Time-series Dense Encoder (arXiv:2304.08424; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-13 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SVGDreamer: Text Guided SVG Generation with Diffusion Model (arXiv:2312.16476; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
NVIDIA/DeepLearningExamples pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified) and HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis (arXiv:2010.05646; that paper's own run record: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
awslabs/gluon-ts mxnetSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series (arXiv:2108.00981; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
etna-team/etna pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Time-Series Representation Learning via Temporal and Contextual Contrasting (arXiv:2106.14112; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 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

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 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.

1ran · honoured contract
1ran · our draft was wrong
3ran; the contract check could not run
3ran
2unverified

Licence: 5 of the 10 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 4 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.

AWarno/CancerOptimization community (archive-listed) 1 sample, 0 ran · 1 unverified
preprocess_row preprocess_data.py unverified MIT (permissive) · afd2b57d5293817f · report
LiamMaclean216/Any-Coin-TFN community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
a_norm utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7c95cb374bdd7ed4 · report fixture: signature Q:Tensor/3/float, K:Tensor/3/float · returned Tensor · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 3 of 5, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32 · arg 3: rank 3, kind float, dtype float32
utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 72ce5bea9e3abec1 · report fixture: signature Q:Tensor/3/float, K:Tensor/3/float, V:Tensor/3/float · returned Tensor · level recorded 2026-09-22
get_n_params in 21 papers utils.py ran · honoured contract no licence file found · pointer only · 608920c78f1ae5e9 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-22
LiamMaclean216/Temporal-Fusion-Transformer community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
load_data in 700 papers data.py ran · our draft was wrong no licence file found · pointer only · c3f734aa50290d68 · report fixture: signature year:list/1/int, symbol:list/1/str, con_cols:list/1/str, interval:str/0/str, normalise:bool/0/bool · returned DataFrame · level recorded 2026-09-22
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
data.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 7e9f6b9b785a1b6a · report fixture: signature x:Tensor/3/float, dims:list/1/int, gpu:bool/0/bool · returned list · level recorded 2026-09-22
PlaytikaResearch/tft-torch community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
aggregate_weights tft_torch/visualize.py ran MIT (permissive) · b1e5983bdd5cf42a · report fixture: signature output_arr:ndarray/2/float, prctiles:list/1/float, feat_names:list/1/str · returned DataFrame · level recorded 2026-09-24
compute_quantile_loss_instance_wise tft_torch/loss.py ran MIT (permissive) · 8cd61d6b957edb62 · report fixture: signature outputs:Tensor/3/float, targets:Tensor/2/float, desired_quantiles:Tensor/1/float · returned Tensor · level recorded 2026-09-24
get_quantiles_loss_and_q_risk tft_torch/loss.py ran MIT (permissive) · 4c5a235eedb8d13a · report fixture: signature outputs:Tensor/3/float, targets:Tensor/2/float, desired_quantiles:Tensor/1/float · returned tuple · level recorded 2026-09-24
display_sample_wise_selection_stats tft_torch/visualize.py unverified MIT (permissive) · 3af6ae65fe631626 · report

Tasks

Interpretable Machine LearningTime SeriesTime Series AnalysisTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutInterpretabilityLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual 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