Methods › General › Attention Modules › Attention Free Transformer

Attention Free Transformer

3 papers tagged archive 2025-07-28

Introduced by Shuangfei Zhai et al. in An Attention Free Transformer

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

Attention Free Transformer, or AFT, is an efficient variant of a multi-head attention module that eschews dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the result of which is multiplied with the query in an element-wise fashion. This new operation has a memory complexity linear w.r.t. both the context size and the dimension of features, making it compatible to both large input and model sizes.

Given the input X, AFT first linearly transforms them into Q=X W^Q, K=X Wᴷ, V=X Wⱽ, then performs following operation:

Y=f(X) ; Yₜ=σ_q(Qₜ) ⊙(∑_(t′=1)ᵀ exp(K_(t′)+w_(t, t′)) ⊙V_(t′))/(∑_(t′=1)ᵀ exp(K_(t′)+w_(t, t′)))

where ⊙ is the element-wise product; σ_q is the nonlinearity applied to the query with default being sigmoid; w ∈R^(T ×T) is the learned pair-wise position biases.

Explained in words, for each target position t, AFT performs a weighted average of values, the result of which is combined with the query with element-wise multiplication. In particular, the weighting is simply composed of the keys and a set of learned pair-wise position biases. This provides the immediate advantage of not needing to compute and store the expensive attention matrix, while maintaining the global interactions between query and values as MHA does.

PaperSource

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: Mask-Attention-Free Transformer; Attention Free Transformers (AFT); Hybrid Attention Transformer; Average Attention Transformers; Dual Attention Transformer (DAT); Deformable Attention Transformer; Integrated Attention Transformer; Entanglement-Free Attention (EFA).

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: 3 · with a code link: 1 · where Syntology ran a sample: 1 (1 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 (1 of 3 tagged: 1 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 3 of 3, 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

4 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
Fine-Grained Image Classification1
Image Classification1
Language Modelling1
Position1

Usage over time archive 2025-07-28

Papers per year tagged with Attention Free Transformer: 2021 to 2021, peak 3 3 0 2021: 3 papers 2021
Papers per year the archive tags with this method, by the paper's archive date (3 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