Graph-Agnostic Linear Transformers

Zhiyu Guo

doi:10.1016/j.neunet.2026.108595

Graph-Agnostic Linear Transformers

2026-01-16

0

PRE

AI

DOI：10.1016/j.neunet.2026.108595

Original

Original request for help

Save

Abstract

En 中文

• 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-Agnostic Linear Transformers

Abstract

Journal

Organization