{"url":"/method/linformer","slug":"linformer","name":"Linformer","full_name":"Linformer","full_name_withheld":false,"description_markdown":"**Linformer** is a linear [Transformer](https://paperswithcode.com/method/transformer) that utilises a linear self-attention mechanism to tackle the self-attention bottleneck with [Transformer models](https://paperswithcode.com/methods/category/transformers). The original [scaled dot-product attention](https://paperswithcode.com/method/scaled) 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Linformer: Self-Attention with Linear Complexity","paper":"/paper/linformer-self-attention-with-linear","first_author":"Sinong Wang","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/linformer-self-attention-with-linear"},"source":{"url":"https://arxiv.org/abs/2006.04768v3","title":"Linformer: Self-Attention with Linear Complexity","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Autoregressive Transformers","url":"/methods/category/autoregressive-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":17,"papers_newest_first":[{"paper":null,"title":"CacheFormer: High Attention-Based Segment Caching","date":"2025-04-18","arxiv_id":"2504.13981","n_code_links":0,"syntology":null},{"paper":null,"title":"LinFormer: A Linear-based Lightweight Transformer Architecture For Time-Aware MIMO Channel Prediction","date":"2024-10-28","arxiv_id":"2410.21351","n_code_links":0,"syntology":null},{"paper":"/paper/joint-fine-tuning-and-conversion-of","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","date":"2024-10-09","arxiv_id":"2410.06846","n_code_links":1,"syntology":{"ran":5,"of":5,"unverified":0,"pointer_only":0}},{"paper":null,"title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":null,"title":"Sumformer: Universal Approximation for Efficient Transformers","date":"2023-07-05","arxiv_id":"2307.02301","n_code_links":0,"syntology":null},{"paper":"/paper/mpcvit-searching-for-mpc-friendly-vision","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","date":"2022-11-25","arxiv_id":"2211.13955","n_code_links":1,"syntology":null},{"paper":null,"title":"Treeformer: Dense Gradient Trees for Efficient Attention Computation","date":"2022-08-18","arxiv_id":"2208.09015","n_code_links":0,"syntology":null},{"paper":null,"title":"Linearizing Transformer with Key-Value Memory","date":"2022-03-23","arxiv_id":"2203.12644","n_code_links":0,"syntology":null},{"paper":"/paper/sketching-as-a-tool-for-understanding-and","title":"Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences","date":"2021-12-10","arxiv_id":"2112.05359","n_code_links":1,"syntology":null},{"paper":null,"title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","date":"2021-08-24","arxiv_id":"2108.10808","n_code_links":0,"syntology":null},{"paper":"/paper/vision-xformers-efficient-attention-for-image","title":"Vision Xformers: Efficient Attention for Image Classification","date":"2021-07-05","arxiv_id":"2107.02239","n_code_links":2,"syntology":null},{"paper":"/paper/styleformer-transformer-based-generative","title":"Styleformer: Transformer based Generative Adversarial Networks with Style Vector","date":"2021-06-13","arxiv_id":"2106.07023","n_code_links":3,"syntology":{"ran":4,"of":4,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos","date":"2021-06-07","arxiv_id":"2106.03505","n_code_links":0,"syntology":null},{"paper":null,"title":"A Practical Survey on Faster and Lighter Transformers","date":"2021-03-26","arxiv_id":"2103.14636","n_code_links":0,"syntology":null},{"paper":null,"title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":"/paper/linformer-self-attention-with-linear","title":"Linformer: Self-Attention with Linear Complexity","date":"2020-06-08","arxiv_id":"2006.04768","n_code_links":3,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":2}}],"papers_shown":17,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":null,"name":"GPU","papers":2},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/survey","name":"Survey","papers":2},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deblurring","name":"Deblurring","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/mamba","name":"Mamba","papers":1},{"task":"/task/navigate","name":"Navigate","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1},{"task":null,"name":"Position","papers":1}],"tasks_shown":20,"n_tasks":30,"usage_by_year":[{"year":"2020","papers":3},{"year":"2021","papers":6},{"year":"2022","papers":3},{"year":"2023","papers":1},{"year":"2024","papers":3},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/linformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}