Methods › General › Attention Modules › Graph Self-Attention

Graph Self-Attention

64 papers tagged archive 2025-07-28

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

Graph Self-Attention (GSA) is a self-attention module used in the BP-Transformer architecture, and is based on the graph attentional layer.

For a given node u, we update its representation according to its neighbour nodes, formulated as hᵤ ←GSA(𝒢, hᵘ).

Let A(u) denote the set of the neighbour nodes of u in 𝒢, GSA(𝒢, hᵘ) is detailed as follows:

Aᵘ = concat({hᵥ | v ∈𝒜(u)})

Qᵘᵢ = HₖW^Qᵢ,Kᵢᵘ = AᵘWᴷᵢ,Vᵘᵢ = AᵘWᵢⱽ

headᵘᵢ = softmax(QᵘᵢKᵢᵘᵀ/(√(d)))Vᵢᵘ

GSA(𝒢, hᵘ) = [headᵘ₁, …, headᵘₕ]Wᴼ

where d is the dimension of h, and W^Qᵢ, Wᴷᵢ and Wⱽᵢ are trainable parameters of the i-th attention head.

Source: BP-Transformer: Modelling Long-Range Context via Binary...See Code · yzh119/BPT

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: Attention Graphons; Power Law Graph Attention; Hop Graph Attention (HGA); Omni Self-Attention (OSA); self-modulating attention; Orthogonal Self-Attention; Local Self-Attention Block; Self-Graph Reasoning (SGR).

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: 64 · with a code link: 19 · where Syntology ran a sample: 3 (3 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 (3 of 64 tagged: 3 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 64 of 64, 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 86 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 Attention3
Graph Classification3
Representation Learning3
Sentence3
Translation3
Abstractive Dialogue Summarization2
Anomaly Detection2
Articles2
Autonomous Driving2
BIG-bench Machine Learning2
Graph Regression2
Graph Representation Learning2
Language Modeling2
Language Modelling2
Machine Translation2
Molecular Property Prediction2
Sentiment Analysis2
Aspect-Based Sentiment Analysis (ABSA)1
Attribute1
Autonomous Vehicles1

Usage over time archive 2025-07-28

Papers per year tagged with Graph Self-Attention: 2019 to 2025, peak 17 17 0 2019: 1 paper 2019 2020: 4 papers 2020 2021: 9 papers 2021 2022: 10 papers 2022 2023: 17 papers 2023 2024: 13 papers 2024 2025: 10 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (64 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