{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/linformer-self-attention-with-linear","title":"Linformer: Self-Attention with Linear Complexity","arxiv_id":"2006.04768","date":"2020-06-08","proceeding":null,"authors":["Sinong Wang","Belinda Z. Li","Madian Khabsa","Han Fang","Hao Ma"],"abstract":"Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences, as the standard self-attention mechanism of the Transformer uses $O(n^2)$ time and space with respect to sequence length. In this paper, we demonstrate that the self-attention mechanism can be approximated by a low-rank matrix. We further exploit this finding to propose a new self-attention mechanism, which reduces the overall self-attention complexity from $O(n^2)$ to $O(n)$ in both time and space. The resulting linear transformer, the \\textit{Linformer}, performs on par with standard Transformer models, while being much more memory- and time-efficient.","url_abs":"https://arxiv.org/abs/2006.04768v3","url_pdf":"https://arxiv.org/pdf/2006.04768v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"linformer-self-attention-with-linear","repo_url":"https://github.com/facebookresearch/fairseq/tree/main/examples/linformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"linformer-self-attention-with-linear","repo_url":"https://github.com/kuixu/Linear-Multihead-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"linformer-self-attention-with-linear","repo_url":"https://github.com/tatp22/linformer-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linformer","method_name":"Linformer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"multi-head-linear-attention","method_name":"Multi-Head Linear Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"linformer","name":"Linformer","full_name":"Linformer"},{"slug":"multi-head-linear-attention","name":"Multi-Head Linear Attention","full_name":"Multi-Head Linear Attention"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.04768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04768"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/fairseq/tree/main/examples/linformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tatp22/linformer-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kuixu/Linear-Multihead-Attention","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"4ed834b7676d8783","entry":"gen_causal_mask","repo":"tatp22/linformer-pytorch","repo_kind":"listed","path":"linformer_pytorch/linformer_pytorch.py","file_url":"https://github.com/tatp22/linformer-pytorch/blob/HEAD/linformer_pytorch/linformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ed834b7676d8783"}},{"code_sha256_prefix":"289eea67db7520a9","entry":"get_act","repo":"tatp22/linformer-pytorch","repo_kind":"listed","path":"linformer_pytorch/linformer_pytorch.py","file_url":"https://github.com/tatp22/linformer-pytorch/blob/HEAD/linformer_pytorch/linformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"289eea67db7520a9"}},{"code_sha256_prefix":"caeb28d34b34bc2a","entry":"identity","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"caeb28d34b34bc2a"}},{"code_sha256_prefix":"7255bb9dcda93e92","entry":"linear_multi_head_attention_forward","repo":"kuixu/Linear-Multihead-Attention","repo_kind":"listed","path":"linear_multihead_attention.py","file_url":"https://github.com/kuixu/Linear-Multihead-Attention/blob/HEAD/linear_multihead_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7255bb9dcda93e92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}