{"url":"/method/sinkhorn-transformer","slug":"sinkhorn-transformer","name":"Sinkhorn Transformer","full_name":"Sinkhorn Transformer","full_name_withheld":false,"description_markdown":"The **Sinkhorn Transformer** is a type of [transformer](https://paperswithcode.com/method/transformer) that uses [Sparse Sinkhorn Attention](https://paperswithcode.com/method/sparse-sinkhorn-attention) as a building block. This component is a plug-in replacement for dense fully-connected attention (as well as local attention, and sparse attention alternatives), and allows for reduced memory complexity as well as sparse attention.","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":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":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"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}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2020","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/sinkhorn-transformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}