Methods › General › Attention Modules › Multi-Head Attention

Multi-Head Attention

24,855 papers tagged archive 2025-07-28

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

Multi-head Attention is a module for attention mechanisms which runs through an attention mechanism several times in parallel. The independent attention outputs are then concatenated and linearly transformed into the expected dimension. Intuitively, multiple attention heads allows for attending to parts of the sequence differently (e.g. longer-term dependencies versus shorter-term dependencies).

MultiHead(Q, K, V) = [head₁,…,headₕ]W₀

where headᵢ = Attention (QWᵢ^Q, KWᵢᴷ, VWᵢⱽ )

Above W are all learnable parameter matrices.

Note that scaled dot-product attention is most commonly used in this module, although in principle it can be swapped out for other types of attention mechanism.

Source: Lilian Weng

Source: Attention Is All You NeedSee Code · jadore801120/attention-is-all-you-need-pytorch

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “Multi-Head Attention: Collaborate Instead of Concatenate” (arXiv:2006.16362, 191 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:2006.16362: its page on this site · ask the lookup about it.

Near matches the lookup lists, each a different name: Multi-Head Knowledge Attention; multi-head attention neural network; Multi-head Explicit Attention (MEA); Gaussian Multi-head Attention (GMA); Multihead Low-Rank Attention (MLRA); Multi-head Attention Fusion Network; Multi-Head Low-Rank Attention (MLRA); Multi-Head Tropical Attention (MHTA).

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: 24,855 · with a code link: 11,214 · where Syntology ran a sample: 3,454 (2,813 with a run with no instrument failure, 641 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3,454 of 24,855 tagged: 2,813 with a run with no instrument failure, 641 where every run was a failure of Syntology's instrument)

Page 1 of 249: papers 1 to 100 of 24,855, 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 2,604 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 Modelling3,000
Language Modeling2,346
Retrieval1,792
Question Answering1,481
Decoder1,392
Sentence1,337
RAG1,320
Retrieval-augmented Generation1,149
Translation1,035
Machine Translation929
Semantic Segmentation859
Large Language Model836
Text Generation762
Transfer Learning713
Image Classification709
Object Detection665
Representation Learning630
Sentiment Analysis614
Classification607
Segmentation596

Usage over time archive 2025-07-28

Papers per year tagged with Multi-Head Attention: 2017 to 2025, peak 7,098 7,098 0 2017: 22 papers 2017 2018: 126 papers 2018 2019: 1081 papers 2019 2020: 2162 papers 2020 2021: 3154 papers 2021 2022: 3332 papers 2022 2023: 5274 papers 2023 2024: 7098 papers 2024 2025: 2606 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (24,855 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 Modules

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