Methods › Natural Language Processing › Autoregressive Transformers › Linformer
Linformer
Introduced by Sinong Wang et al. in Linformer: Self-Attention with Linear Complexity
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Linformer is a linear Transformer that utilises a linear self-attention mechanism to tackle the self-attention bottleneck with Transformer models. The original scaled dot-product attention is decomposed into multiple smaller attentions through linear projections, such that the combination of these operations forms a low-rank factorization of the original attention.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2006.04768'). Repositories: 3 listed of 3 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2006.04768, not a method entry. This answer is about arXiv:2006.04768, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2006.04768 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 2 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 17 · with a code link: 6 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 17 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 17 of 17, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
CacheFormer: High Attention-Based Segment Caching 18 Apr 2025 · 0 repositories · arXiv:2504.13981
-
LinFormer: A Linear-based Lightweight Transformer Architecture For Time-Aware MIMO Channel Prediction 28 Oct 2024 · 0 repositories · arXiv:2410.21351
-
Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity 9 Oct 2024 · 1 repository · arXiv:2410.06846Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction 1 Oct 2024 · 0 repositories · arXiv:2410.00380
-
Sumformer: Universal Approximation for Efficient Transformers 5 Jul 2023 · 0 repositories · arXiv:2307.02301
-
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention 25 Nov 2022 · 1 repository · arXiv:2211.13955
-
Treeformer: Dense Gradient Trees for Efficient Attention Computation 18 Aug 2022 · 0 repositories · arXiv:2208.09015
-
Linearizing Transformer with Key-Value Memory 23 Mar 2022 · 0 repositories · arXiv:2203.12644
-
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences 10 Dec 2021 · 1 repository · arXiv:2112.05359
-
Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation 24 Aug 2021 · 0 repositories · arXiv:2108.10808
-
Vision Xformers: Efficient Attention for Image Classification 5 Jul 2021 · 2 repositories · arXiv:2107.02239
-
Styleformer: Transformer based Generative Adversarial Networks with Style Vector 13 Jun 2021 · 3 repositories · arXiv:2106.07023Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos 7 Jun 2021 · 0 repositories · arXiv:2106.03505
-
A Practical Survey on Faster and Lighter Transformers 26 Mar 2021 · 0 repositories · arXiv:2103.14636
-
Revisiting Linformer with a modified self-attention with linear complexity 16 Dec 2020 · 0 repositories · arXiv:2101.10277
-
Efficient Transformers: A Survey 14 Sep 2020 · 0 repositories · arXiv:2009.06732
-
Linformer: Self-Attention with Linear Complexity 8 Jun 2020 · 3 repositories · arXiv:2006.04768Syntology official: no sample here; runs from other or unrecorded repositories · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 30 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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