{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","name":"Sparse Sinkhorn Attention","full_name":"Sparse Sinkhorn Attention","full_name_withheld":false,"description_markdown":"**Sparse Sinkhorn Attention** is an attention mechanism that reduces the memory complexity of the [dot-product attention mechanism](https://paperswithcode.com/method/scaled) and is capable of learning sparse attention outputs. It is based on the idea of differentiable sorting of internal representations within the self-attention module. SSA incorporates a meta sorting network that learns to rearrange and sort input sequences. Sinkhorn normalization is used to normalize the rows and columns of the sorting matrix. The actual SSA attention mechanism then acts on the block sorted sequences.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Sparse Sinkhorn Attention","paper":"/paper/sparse-sinkhorn-attention","first_author":"Yi Tay","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sparse-sinkhorn-attention"},"source":{"url":"https://arxiv.org/abs/2002.11296v1","title":"Sparse Sinkhorn Attention","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/lucidrains/sinkhorn-transformer/blob/3eaa76e99efeee75cf8298defaaef51621c55ff4/sinkhorn_transformer/sinkhorn_transformer.py#L286","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Attention Mechanisms","url":"/methods/category/attention-mechanisms","pwc_aliases":["attention-mechanisms-1"]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/vtp-volumetric-transformer-for-multi-view","slug":"vtp-volumetric-transformer-for-multi-view","title":"VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation","date":"2022-05-25","arxiv_id":"2205.12602","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","n_code_links":1,"syntology":null}],"papers_shown":2,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":2,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/3d-human-pose-estimation","name":"3D Human Pose Estimation","papers":1},{"task":"/task/3d-multi-person-pose-estimation","name":"3D Multi-Person Pose Estimation","papers":1},{"task":"/task/3d-pose-estimation","name":"3D Pose Estimation","papers":1},{"task":"/task/document-classification","name":"Document Classification","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/pose-estimation","name":"Pose Estimation","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","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/sparse-sinkhorn-attention"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Sparse%20Sinkhorn%20Attention","read_at":"2026-10-05T01:02:18+00:00","query":"Sparse Sinkhorn Attention","kind":"paper","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2002.11296"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2002.11296","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2002.11296","citations":406},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Sparse Sinkhorn Attention'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2002.11296","page":"/paper/sparse-sinkhorn-attention","syntology_url":"https://syntology.ai/paper/2002.11296","in_graph_layer":false,"samples":0},"line":"repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub). The lookup matched a paper by its title, arXiv:2002.11296, not a method entry. This answer is about arXiv:2002.11296, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"89d224ccca99741cfe6b66e42f75ad11c2b43f23cc2caf69f048bd437f910897","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}