Papers › First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

15 Dec 2022arXiv:2212.08151archive 2025-07-28

Xiyuan Zhang, Xiaoyong Jin, Karthick Gopalswamy, Gaurav Gupta, Youngsuk Park, Xingjian Shi, Hao Wang, Danielle C. Maddix, Yuyang Wang

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in frequency domains (e.g., Fourier domain, wavelet domain), given that seasonal patterns can be better captured in these domains. In this work, we seek to understand the relationships between attention models in different time and frequency domains. Theoretically, we show that attention models in different domains are equivalent under linear conditions (i.e., linear kernel to attention scores). Empirically, we analyze how attention models of different domains show different behaviors through various synthetic experiments with seasonality, trend and noise, with emphasis on the role of softmax operation therein. Both these theoretical and empirical analyses motivate us to propose a new method: TDformer (Trend Decomposition Transformer), that first applies seasonal-trend decomposition, and then additively combines an MLP which predicts the trend component with Fourier attention which predicts the seasonal component to obtain the final prediction. Extensive experiments on benchmark time-series forecasting datasets demonstrate that TDformer achieves state-of-the-art performance against existing attention-based models.

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: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 17 samples from 1 repository, 14 ran (14 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.

BeBeYourLove/TDformer pytorchSyntology: 17 samples, 14 ran (0 instrument-failed) · 3 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: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

14ran
3unverified

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 BeBeYourLove/TDformer. “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.

BeBeYourLove/TDformer community (archive-listed) 17 samples, 14 ran (0 instrument-failed) · 3 unverified
DataEmbedding in 9 papers model/TDformer.py ran no licence file found · pointer only · 68aca50b866b5c44 · report fixture: signature x:Tensor/3/float, x_mark:Tensor/3/int · returned Tensor · level recorded 2026-09-24
DecoderLayer in 43 papers model/TDformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · a764d7bf11731507 · report fixture: signature x:Tensor/3/float, cross:Tensor/3/float, x_mask:NoneType/0/?, cross_mask:NoneType/0/? · returned tuple · level recorded 2026-09-22
Encoder in 278 papers model/TDformer.py ran fingerprinted no licence file found · pointer only · 262ec83d671e7e73 · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
EncoderLayer in 73 papers model/TDformer.py ran fingerprinted no licence file found · pointer only · 13ebf522358d72ce · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
FixedEmbedding in 6 papers model/TDformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 16e89fafa4d72549 · report fixture: signature x:Tensor/2/int · returned Tensor · level recorded 2026-09-22
FourierAttention model/TDformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · e25d8996d3335ae8 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float, mask:NoneType/0/? · returned tuple · level recorded 2026-09-22
FullAttention in 10 papers model/TDformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · cf298e4e52b231ae · report fixture: signature queries:Tensor/4/float, keys:Tensor/4/float, values:Tensor/4/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
model/TDformer.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · cc9347d9fcbd79f0 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
RevIN in 13 papers model/TDformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 63e737eb80bffe5c · report fixture: signature x:Tensor/3/float, mode:str/0/str · returned Tensor · level recorded 2026-09-22
TemporalEmbedding in 7 papers model/TDformer.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 0047413d8e7fb6de · report fixture: signature x:Tensor/3/int · returned Tensor · level recorded 2026-09-22
TokenEmbedding in 11 papers model/TDformer.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · a06a4f88ba660a18 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
moving_avg in 8 papers model/TDformer.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 94ce7d58219032b2 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
series_decomp in 6 papers model/TDformer.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · e8b308d6f4a51e9c · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22
series_decomp_multi model/TDformer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 24c312878bd471eb · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22
AttentionLayer in 30 papers model/TDformer.py unverified no licence file found · pointer only · 626ecbcf3c8c36f8 · report
Decoder in 210 papers model/TDformer.py unverified no licence file found · pointer only · 2f76a320461e09fc · report
Model in 227 papers model/TDformer.py unverified no licence file found · pointer only · f2783576a62ba4e8 · 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 TDformer (Trend Decomposition Transformer) (graph method: TDformer (Trend Decomposition Transformer)). 19 bricks; individually on a fixture: 16 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; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. Model entry · level 0 · unverified · f2783576a62ba4e8
  2. AttentionLayer model · level 0 · unverified · 626ecbcf3c8c36f8
  3. DataEmbedding helper · level 1 · ran · 68aca50b866b5c44
  4. Decoder model · level 0 · unverified · 2f76a320461e09fc
  5. DecoderLayer model · level 1 · ran · a764d7bf11731507
  6. Encoder model · level 1 · ran · 262ec83d671e7e73
  7. EncoderLayer model · level 1 · ran · 13ebf522358d72ce
  8. FourierAttention helper · level 1 · ran · e25d8996d3335ae8
  9. FullAttention helper · level 1 · ran · cf298e4e52b231ae
  10. RevIN helper · level 1 · ran · 63e737eb80bffe5c
  11. series_decomp helper · level 1 · ran · e8b308d6f4a51e9c
  12. series_decomp_multi helper · level 1 · ran · 24c312878bd471eb
  13. PositionalEmbedding helper · level 1 · ran · cc9347d9fcbd79f0
  14. TemporalEmbedding helper · level 1 · ran · 0047413d8e7fb6de
  15. TimeFeatureEmbedding helper · level 1 · ran · 98a0817e251d19c7
  16. TokenEmbedding helper · level 1 · ran · a06a4f88ba660a18
  17. TriangularCausalMask helper · level 1 · ran · a297b58f69588d02
  18. moving_avg helper · level 1 · ran · 94ce7d58219032b2
  19. FixedEmbedding helper · level 1 · ran · 16e89fafa4d72549

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="2212.08151") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Time SeriesTime Series AnalysisTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Softmax

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