{"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/lsh-attention","slug":"lsh-attention","name":"LSH Attention","full_name":"Locality Sensitive Hashing Attention","full_name_withheld":false,"description_markdown":"**LSH Attention**, or **Locality Sensitive Hashing Attention** is a replacement for [dot-product attention](https://paperswithcode.com/method/scaled) with one that uses locality-sensitive hashing, changing its complexity from O($L^2$) to O($L\\log L$), where $L$ is the length of the sequence. LSH refers to a family of functions (known as LSH families) to hash data points into buckets so that data points near each other are located in the same buckets with high probability, while data points far from each other are likely to be in different buckets. It was proposed as part of the [Reformer](https://paperswithcode.com/method/reformer) architecture.","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/2001.04451v2","title":"Reformer: The Efficient Transformer","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/google/trax/blob/af3a38917bd1bc69cf5d25ce007e16185f22f050/trax/layers/research/efficient_attention.py#L1084","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":22,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/cardioformer-advancing-ai-in-ecg-analysis","slug":"cardioformer-advancing-ai-in-ecg-analysis","title":"Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet","date":"2025-05-08","arxiv_id":"2505.05538","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-powerformer-a-memory-efficient","title":"Fast-Powerformer: A Memory-Efficient Transformer for Accurate Mid-Term Wind Power Forecasting","date":"2025-04-15","arxiv_id":"2504.10923","n_code_links":0,"syntology":null},{"paper":null,"slug":"reformer-generating-radio-fakes-for-data","title":"ReFormer: Generating Radio Fakes for Data Augmentation","date":"2024-12-31","arxiv_id":"2501.00282","n_code_links":0,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","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,"slug":"masked-face-recognition-with-generative-to","title":"Masked Face Recognition with Generative-to-Discriminative Representations","date":"2024-05-27","arxiv_id":"2405.16761","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-transformer-based-approach-for-soil","title":"A novel transformer-based approach for soil temperature prediction","date":"2023-11-20","arxiv_id":"2311.11626","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalrelectra-mixed-domain-language-modeling","title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","date":"2022-12-16","arxiv_id":"2212.08204","n_code_links":0,"syntology":null},{"paper":"/paper/fecam-frequency-enhanced-channel-attention","slug":"fecam-frequency-enhanced-channel-attention","title":"FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting","date":"2022-12-02","arxiv_id":"2212.01209","n_code_links":1,"syntology":null},{"paper":"/paper/non-stationary-transformers-rethinking-the","slug":"non-stationary-transformers-rethinking-the","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","date":"2022-05-28","arxiv_id":"2205.14415","n_code_links":2,"syntology":null},{"paper":null,"slug":"discovering-material-information-using","title":"Discovering material information using hierarchical Reformer model on financial regulatory filings","date":"2022-03-28","arxiv_id":"2204.05979","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-token-normalization-improves-vision-1","slug":"dynamic-token-normalization-improves-vision-1","title":"Dynamic Token Normalization Improves Vision Transformers","date":"2021-12-05","arxiv_id":"2112.02624","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["wqshao126/dtn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hierarchical-transformers-are-more-efficient","slug":"hierarchical-transformers-are-more-efficient","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2021-10-26","arxiv_id":"2110.13711","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google/trax"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/end-to-end-user-behavior-retrieval-in-click","slug":"end-to-end-user-behavior-retrieval-in-click","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","date":"2021-08-10","arxiv_id":"2108.04468","n_code_links":1,"syntology":null},{"paper":"/paper/reformer-the-relational-transformer-for-image","slug":"reformer-the-relational-transformer-for-image","title":"ReFormer: The Relational Transformer for Image Captioning","date":"2021-07-29","arxiv_id":"2107.14178","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-practical-survey-on-faster-and-lighter","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,"slug":"reassert-deep-learning-for-assert-generation","title":"ReAssert: Deep Learning for Assert Generation","date":"2020-11-19","arxiv_id":"2011.09784","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-unknot","title":"Learning to Unknot","date":"2020-10-28","arxiv_id":"2010.16263","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustification-of-segmentation-models","title":"Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging","date":"2020-09-23","arxiv_id":"2009.11090","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformers-a-survey","title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":"/paper/segmenting-scientific-abstracts-into","slug":"segmenting-scientific-abstracts-into","title":"Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Data","date":"2020-05-11","arxiv_id":"2005.05414","n_code_links":1,"syntology":null},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","n_code_links":10,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google/trax"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":22,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":22,"with_a_code_link":10,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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":3,"papers_where_code_ran_first_page":"/method/lsh-attention/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/lsh-attention/papers/ran/1","json":"/method/lsh-attention/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":"/task/deep-learning","name":"Deep Learning","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/sentence","name":"Sentence","papers":2},{"task":"/task/survey","name":"Survey","papers":2},{"task":"/task/time-series-1","name":"Time Series","papers":2},{"task":"/task/time-series","name":"Time Series Analysis","papers":2},{"task":"/task/time-series-forecasting","name":"Time Series Forecasting","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/binary-classification","name":"Binary Classification","papers":1},{"task":"/task/click-through-rate-prediction","name":"Click-Through Rate Prediction","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/d4rl","name":"D4RL","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deblurring","name":"Deblurring","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1}],"tasks_shown":20,"n_tasks":50,"usage_by_year":[{"year":"2020","papers":7},{"year":"2021","papers":5},{"year":"2022","papers":4},{"year":"2023","papers":1},{"year":"2024","papers":3},{"year":"2025","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/lsh-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=LSH%20Attention","read_at":"2026-10-05T00:58:47+00:00","query":"LSH Attention","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'LSH Attention' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["LSH-MoE","C-kNN-LSH","EL-Attention","TF-ATTENTION","TC-ATTENTION","SS-Attention","Spectral-LSH","VC-Attention"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"4fc2d11c143afd59c69a3634354a7e2be222e8c31ea66442c27d22c5aff8fa1d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}