Methods › General › Attention Modules › Multi-Head Linear Attention
Multi-Head Linear Attention
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.
Multi-Head Linear Attention is a type of linear multi-head self-attention module, proposed with the Linformer architecture. The main idea is to add two linear projection matrices Eᵢ, Fᵢ ∈ℝ^(n×k) when computing key and value. We first project the original (n ×d)-dimensional key and value layers KWᵢᴷ and VWᵢⱽ into (k×d)-dimensional projected key and value layers. We then compute a (n×k) dimensional context mapping P̅ using scaled-dot product attention:
h̅e̅a̅d̅ᵢ̅ = Attention(QW^Qᵢ, EᵢKWᵢᴷ, FᵢVWᵢⱽ)
h̅e̅a̅d̅ᵢ̅ = softmax((QW^Qᵢ(EᵢKWᵢᴷ)ᵀ)/(√(dₖ))) ·FᵢVWᵢⱽ
Finally, we compute context embeddings for each head using P̅ ·(FᵢVWᵢⱽ).
Papers archive 2025-07-28
24 shown of 24, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device 12 Jun 2025 · 0 repositories · arXiv:2506.10361
-
CacheFormer: High Attention-Based Segment Caching 18 Apr 2025 · 0 repositories · arXiv:2504.13981
-
HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution 4 Dec 2024 · 0 repositories · arXiv:2412.03748
-
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 ran 5 of 5 samples · 0 unverified
-
GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction 1 Oct 2024 · 0 repositories · arXiv:2410.00380
-
Attention as a Hypernetwork 9 Jun 2024 · 1 repository · arXiv:2406.05816Syntology ran 1 of 1 samples · 0 unverified
-
Sumformer: Universal Approximation for Efficient Transformers 5 Jul 2023 · 0 repositories · arXiv:2307.02301
-
RedMotion: Motion Prediction via Redundancy Reduction 19 Jun 2023 · 3 repositories · arXiv:2306.10840Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
UMat: Uncertainty-Aware Single Image High Resolution Material Capture 25 May 2023 · 0 repositories · arXiv:2305.16312
-
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
-
Rethinking Attention Mechanism in Time Series Classification 14 Jul 2022 · 0 repositories · arXiv:2207.07564
-
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 ran 4 of 4 samples · 0 unverified
-
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
-
Multi-Head Linear Attention Generative Adversarial Network for Thin Cloud Removal 20 Dec 2020 · 0 repositories · arXiv:2012.10898
-
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 ran 3 of 4 samples · 1 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 48 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Knowledge Distillation | 3 |
| Language Modelling | 3 |
| Classification | 2 |
| GPU | 2 |
| Language Modeling | 2 |
| Prediction | 2 |
| Survey | 2 |
| Abstractive Text Summarization | 1 |
| Active Learning | 1 |
| Autonomous Driving | 1 |
| Cloud Removal | 1 |
| Data Augmentation | 1 |
| Deblurring | 1 |
| Decoder | 1 |
| Depth Estimation | 1 |
| Face Recognition | 1 |
| Generative Adversarial Network | 1 |
| Image Classification | 1 |
| Image Generation | 1 |
| Image Restoration | 1 |
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