AI Paper Atlas

Research map / Graph learning / GNN architectures

GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization

Huizhe Zhang, Jintang Li, Yuchang Zhu, Huazhen Zhong, Liang Chen

AAAI 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use spiking node tokenization with codebook guided attention instead of Performer (ablation)GT-SNT · ogbn-arxivaccuracy (%): 71.2 -> 72.4Improved
use CGSA instead of Linformer (ablation)GT-SNT · ogbn-arxivaccuracy (%): 65.2 -> 72.4Improved
use spiking node tokenization instead of VQ-VAE codebook (ablation)GT-SNT · PubMedaccuracy (%): 79.8 -> 80.6Improved
use spiking node tokenization instead of FSQ (ablation)GT-SNT · PubMedaccuracy (%): 78.4 -> 80.6Improved
use spiking node tokenization instead of FSQ (ablation)GT-SNT · Co-CSaccuracy (%): 93.7 -> 93.7No clear effect
use PLIF spiking neuron instead of IF (ablation)GT-SNT · PubMedaccuracy (%): 81.6 -> 80.6Hurt
use PLIF spiking neuron instead of LIF (ablation)GT-SNT · PubMedaccuracy (%): 79.6 -> 80.6Improved
use STFNorm instead of LayerNorm (ablation)GT-SNT · PubMedaccuracy (%): 78.9 -> 80.6Improved
swap GT-SNT's normalization to STFNorm variant (ablation)GT-SNT · PubMedaccuracy (%): 80.6 -> 82.6Improved
use spiking node tokenization instead of repeated-graph or retrieval-based tokenizationGT-SNT · Co-Physics inferenceinference latency (s): 2.60 -> 0.02Improved
build tokens from spike counts instead of pre-defined VQ codebookGT-SNT · Cora and CS codebook usagecodebook usage: GOAT 10.6% and VQGraph 16.9% (Cora) -> 100%Improved
increase propagation steps T beyond 6 (ablation)GT-SNT · Cora and CSaccuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 5 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy