Graph-Agnostic Linear Transformers

•Propose GALiT, a novel graph-agnostic linear Transformer for graph-structured data.•Decouple graph structures from Transformers to reduce complexity.•Achieve superior performance compared to existing GNNs and Graph Transformers. Graph Transformers (GTs), as emerging foundational encoders for graph-...

Full description

Saved in:
Bibliographic Details
Published in:Neural networks 2026-06, Vol.198, p.108595, Article 108595
Main Authors: Guo, Zhiyu, Liu, Yang, Ao, Xiang, Tang, Yateng, Chen, Xinhuan, Zheng, Xuehao, He, Qing
Format: Article
Language:English
Subjects:
Algorithms
Computer Graphics
Graph neural network
Graph transformer
Graph-agnostic model
Humans
Linear attention
Linear Models
Neural Networks, Computer
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!