Methods › General › Attention Mechanisms › LSH Attention

Locality Sensitive Hashing Attention

LSH Attention

22 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

LSH Attention, or Locality Sensitive Hashing Attention is a replacement for dot-product attention with one that uses locality-sensitive hashing, changing its complexity from O(L²) to O(LlogL), 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 architecture.

Source: Reformer: The Efficient TransformerSee Code · google/trax

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: LSH-MoE; C-kNN-LSH; EL-Attention; TF-ATTENTION; TC-ATTENTION; SS-Attention; Spectral-LSH; VC-Attention.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 22 · with a code link: 10 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3 of 22 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 22 of 22, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 50 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling3
Deep Learning2
Image Generation2
Language Modeling2
Reinforcement Learning (RL)2
Segmentation2
Sentence2
Survey2
Time Series2
Time Series Analysis2
Time Series Forecasting2
Attribute1
BIG-bench Machine Learning1
Binary Classification1
Click-Through Rate Prediction1
Computational Efficiency1
D4RL1
Data Augmentation1
Deblurring1
Decoder1

Usage over time archive 2025-07-28

Papers per year tagged with LSH Attention: 2020 to 2025, peak 7 7 0 2020: 7 papers 2020 2021: 5 papers 2021 2022: 4 papers 2022 2023: 1 paper 2023 2024: 3 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (22 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Attention Mechanisms

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections