Papers › Are Self-Attentions Effective for Time Series Forecasting?

Are Self-Attentions Effective for Time Series Forecasting?

27 May 2024arXiv:2405.16877archive 2025-07-28

Dongbin Kim, Jinseong Park, Jaewook Lee, Hoki Kim

Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasting, their effectiveness remains debated. Recent findings have indicated that simpler linear models might outperform complex Transformer-based approaches, highlighting the potential for more streamlined architectures. In this paper, we shift the focus from evaluating the overall Transformer architecture to specifically examining the effectiveness of self-attention for time series forecasting. To this end, we introduce a new architecture, Cross-Attention-only Time Series transformer (CATS), that rethinks the traditional Transformer framework by eliminating self-attention and leveraging cross-attention mechanisms instead. By establishing future horizon-dependent parameters as queries and enhanced parameter sharing, our model not only improves long-term forecasting accuracy but also reduces the number of parameters and memory usage. Extensive experiment across various datasets demonstrates that our model achieves superior performance with the lowest mean squared error and uses fewer parameters compared to existing models. The implementation of our model is available at: https://github.com/dongbeank/CATS.

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 13 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 5 ran (5 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.

dongbeank/cats officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 5 ran (0 instrument-failed) · 8 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

13 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 8 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.

1ran · honoured contract
4ran
8unverified

Licence: 3 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 dongbeank/cats. “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.

dongbeank/cats official repository 13 samples, 5 ran (0 instrument-failed) · 8 unverified
DecoderLayer in 43 papers models/CATS.py ran MIT (permissive) · 5b900d79dd00feb4 · report fixture: signature seq:Tensor/3/float, pred:Tensor/3/float, prev:NoneType/0/? · returned tuple · level recorded 2026-09-24
Projection in 10 papers models/CATS.py ran · metamorphic tier: invariant MIT (permissive) · c9e915f73a989d19 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
QueryAdaptiveMasking models/CATS.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 51cadb0ea6fdf45c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
_MultiheadAttention in 5 papers models/CATS.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 928f4380b09f0830 · report fixture: signature Q:Tensor/3/float, K:Tensor/3/float, V:Tensor/3/float, prev:NoneType/0/? · returned tuple · level recorded 2026-09-22
parse_ratios utils/tools.py ran · honoured contract MIT (permissive) · cb391e8599bbce03 · report fixture: signature ratio_string:str/0/str · returned list · level recorded 2026-09-24
CORR in 19 papers utils/metrics.py unverified MIT (permissive) here; the stored copy is pointer only · 8c76ef42a9443f81 · report
Decoder in 210 papers models/CATS.py unverified MIT (permissive) · 1a7ac87e34d772f5 · report
Dummy_Embedding models/CATS.py unverified MIT (permissive) · 9362e3c7bb8cc5f2 · report
MAE in 46 papers utils/metrics.py unverified MIT (permissive) here; the stored copy is pointer only · 75f44993b096bf76 · report
Model_backbone models/CATS.py unverified MIT (permissive) · d682a61115f944df · report
RSE in 21 papers utils/metrics.py unverified MIT (permissive) here; the stored copy is pointer only · b40a11875ebd0cd2 · report
time_features in 21 papers utils/timefeatures.py unverified MIT (permissive) · 9a5fcd4ebfc55d03 · report
time_features_from_frequency_str in 20 papers utils/timefeatures.py unverified MIT (permissive) · f8544563682146e5 · 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 Cross-Attention-only Time Series transformer (CATS) (graph method: Cross-Attention-only Time Series transformer (CATS)). 8 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. Model_backbone entry · level 0 · unverified · d682a61115f944df
  2. Dummy_Embedding model · level 0 · unverified · 9362e3c7bb8cc5f2
  3. Projection model · level 1 · ran · c9e915f73a989d19
  4. Decoder model · level 0 · unverified · 1a7ac87e34d772f5
  5. DecoderLayer model · level 1 · ran · 5b900d79dd00feb4
  6. GEGLU helper · level 1 · ran · c83d2ae566da79c3
  7. QueryAdaptiveMasking helper · level 1 · ran · 51cadb0ea6fdf45c
  8. _MultiheadAttention model · level 1 · ran · 928f4380b09f0830

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="2405.16877") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Time SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusLabel SmoothingLayer NormalizationLinear LayerMulti-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