Methods › General › Attention Mechanisms › Multiplicative Attention
Multiplicative Attention
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.
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).
Papers archive 2025-07-28
6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Hierarchical Attention Models for Multi-Relational Graphs 14 Apr 2024 · 1 repository · arXiv:2404.09365
-
Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning 4 Feb 2024 · 1 repository · arXiv:2402.02334
-
Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognition 5 Aug 2022 · 0 repositories · arXiv:2208.03054
-
Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features 3 Nov 2021 · 1 repository · arXiv:2111.02363Syntology ran 0 of 4 samples · 4 unverified
-
STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model 9 Nov 2020 · 1 repository · arXiv:2011.04292
-
Effective Approaches to Attention-based Neural Machine Translation 17 Aug 2015 · 44 repositories · arXiv:1508.04025Syntology ran 2 of 8 samples · 6 unverified · 2 pointer-only (licence)
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.
Usage over time archive 2025-07-28
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
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