</> Code with Papers by Syntology

Methods › General › Attention Mechanisms › FAVOR+

Fast Attention Via Positive Orthogonal Random Features

FAVOR+

102 papers tagged archive 2025-07-28

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

FAVOR+, or Fast Attention Via Positive Orthogonal Random Features, is an efficient attention mechanism used in the Performer architecture which leverages approaches such as kernel methods and random features approximation for approximating softmax and Gaussian kernels.

FAVOR+ works for attention blocks using matrices 𝐀 ∈ℝ^(L×L) of the form 𝐀(i, j) = K(𝐪ᵢᵀ, 𝐤ⱼᵀ), with 𝐪ᵢ/𝐤ⱼ standing for the iᵗʰ/jᵗʰ query/key row-vector in 𝐐/𝐊 and kernel K : ℝᵈ × ℝᵈ →ℝ₊ defined for the (usually randomized) mapping: ϕ: ℝᵈ → ℝʳ₊ (for some r > 0) as:

K(𝐱, 𝐲) = E[ϕ(𝐱)ᵀϕ(𝐲)]

We call ϕ(𝐮) a random feature map for 𝐮 ∈ℝᵈ . For 𝐐^′, 𝐊^′ ∈ℝ^(L ×r) with rows given as ϕ(𝐪ᵢᵀ)ᵀ and ϕ(𝐤ᵢᵀ)ᵀ respectively, this leads directly to the efficient attention mechanism of the form:

Ât̂t̂_̂↔̂(𝐐, 𝐊, 𝐕) = 𝐃̂⁻¹(𝐐^′((𝐊^′)ᵀ𝐕))

where

𝐃̂ = diag(𝐐^′((𝐊^′)1_L))

The above scheme constitutes the FA-part of the FAVOR+ mechanism. The other parts are achieved by:

The details are quite technical, so it is recommended you read the paper for further information on these steps.

Source: Rethinking Attention with Performers

Papers archive 2025-07-28

30 shown of 102, 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.

Tasks archive 2025-07-28

20 shown of 143 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 Modelling6
Decoder5
Time Series5
Classification4
Language Modeling4
Time Series Analysis4
Anomaly Detection3
Computational Efficiency3
Decision Making3
GPU3
Image Classification3
NeRF3
Novel View Synthesis3
Segmentation3
Sentiment Analysis3
image-classification3
Autonomous Driving2
Benchmarking2
Clustering2
Deep Reinforcement Learning2

Usage over time archive 2025-07-28

Papers per year tagged with FAVOR+: 2020 to 2025, peak 25 25 0 2020: 3 papers 2020 2021: 17 papers 2021 2022: 23 papers 2022 2023: 23 papers 2023 2024: 25 papers 2024 2025: 11 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (102 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