Methods › General › Attention Mechanisms › Multiplicative Attention

Multiplicative Attention

6 papers tagged archive 2025-07-28

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

Multiplicative Attention is an attention mechanism where the alignment score function is calculated as:

fₐₜₜ(hᵢ, sⱼ) = hᵢᵀWₐsⱼ

Here h refers to the hidden states for the encoder/source, and s is the hidden states for the decoder/target. The function above is thus a type of alignment score function. We can use a matrix of alignment scores to show the correlation between source and target words, as the Figure to the right shows. Within a neural network, once we have the alignment scores, we calculate the final scores using a softmax function of these alignment scores (ensuring it sums to 1).

Additive and multiplicative attention are similar in complexity, although multiplicative attention is faster and more space-efficient in practice as it can be implemented more efficiently using matrix multiplication. Both variants perform similar for small dimensionality dₕ of the decoder states, but additive attention performs better for larger dimensions. One way to mitigate this is to scale fₐₜₜ(hᵢ, sⱼ) by 1/√(dₕ) as with scaled dot-product attention.

See Code · LukasMut/ATNLP

Source in the archive: Deep Learning for NLP Best Practices by Sebastian Ruder, a link on ruder.io (archive link, not checked and not linked: not a paper host this site links to).

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: TF-ATTENTION; TC-ATTENTION; EL-Attention; SS-Attention; VC-Attention; RBS-Attention; MAC-Attention; max-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: 6 · with a code link: 5 · where Syntology ran a sample: 2 (2 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 (2 of 6 tagged: 2 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 6 of 6, 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

16 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
Graph Attention1
Image-guided Story Ending Generation1
Inductive Bias1
Link Prediction1
Machine Translation1
NER1
NMT1
Named Entity Recognition1
Named Entity Recognition (NER)1
Node Classification1
Prediction1
Relation1
Sentence1
Speech Enhancement1
Translation1
named-entity-recognition1

Usage over time archive 2025-07-28

Papers per year tagged with Multiplicative Attention: 2015 to 2024, peak 2 2 0 2015: 1 paper 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 0 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (6 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