Methods › General › Feedforward Networks › Spatial Gating Unit

Spatial Gating Unit

9 papers tagged archive 2025-07-28

Introduced by Hanxiao Liu et al. in Pay Attention to MLPs

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

Spatial Gating Unit, or SGU, is a gating unit used in the gMLP architecture to captures spatial interactions. To enable cross-token interactions, it is necessary for the layer s(·) to contain a contraction operation over the spatial dimension. The layer s(·) is formulated as the output of linear gating:

s(Z)=Z ⊙f_(W, b)(Z)

where ⊙ denotes element-wise multiplication. For training stability, the authors find it critical to initialize W as near-zero values and b as ones, meaning that f_(W, b)(Z) ≈1 and therefore s(Z) ≈Z at the beginning of training. This initialization ensures each gMLP block behaves like a regular FFN at the early stage of training, where each token is processed independently, and only gradually injects spatial information across tokens during the course of learning.

The authors find it further effective to split Z into two independent parts (Z₁, Z₂) along the channel dimension for the gating function and for the multiplicative bypass:

s(Z)=Z₁ ⊙f_(W, b)(Z₂)

They also normalize the input to f_(W, b) which empirically improved the stability of large NLP models.

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: Spectral Adaptive Gating Unit; Continually-Recyclable Unit-Gating (CRUG); UniT; WM-UniT; VLA-UniT; MM-Spatial; age-gating; Spatial-Gym.

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: 9 · with a code link: 4 · 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 9 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 9 of 9, 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 35 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
Image Classification3
Instance Segmentation2
Object Detection2
Question Answering2
Semantic Segmentation2
object-detection2
All1
Classification1
Common Sense Reasoning1
Decoder1
Deep Learning1
Diversity1
Graph Representation Learning1
Image Compression1
Image Super-Resolution1
In-Context Learning1
Language Modeling1
Language Modelling1
Mixture-of-Experts1
Multi Label Text Classification1

Usage over time archive 2025-07-28

Papers per year tagged with Spatial Gating Unit: 2021 to 2023, peak 4 4 0 2021: 3 papers 2021 2022: 4 papers 2022 2023: 2 papers 2023
Papers per year the archive tags with this method, by the paper's archive date (9 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

Feedforward Networks

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