{"url":"/method/nystr-mformer","slug":"nystr-mformer","name":"Nyströmformer","full_name":"Nyströmformer","full_name_withheld":false,"description_markdown":"Nyströmformer replaces the self-attention in [BERT](https://paperswithcode.com/method/bert)-small and BERT-base using the proposed Nyström approximation. This reduces self-attention complexity to $O(n)$ and allows the [Transformer](https://paperswithcode.com/method/transformer) to support longer sequences.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2102.03902v3","title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/mlpen/Nystromformer/blob/4429fb3ea385dcaeeb76d5e547a03a8a5f40a5bf/code/attention_nystrom.py#L6","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":null,"papers_newest_first":[{"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/nystromformer-a-nystrom-based-algorithm-for","title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","date":"2021-02-07","arxiv_id":"2102.03902","n_code_links":10,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":1}}],"papers_shown":2,"tasks":[{"task":"/task/classification-1","name":"Classification","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2021","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/nystr-mformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}