Polynormer introduces a polynomial-expressive GT model with linear complexity to balance expressivity and scalability. It learns high-degree polynomials controlled by attention scores, achieving superior performance on multiple datasets. The architecture includes local and global equivariant attention models for learning node representations efficiently. Polynormer demonstrates the efficacy of linear local-to-global attention scheme in capturing critical global structures on graphs.
Til et annet språk
fra kildeinnhold
arxiv.org
Viktige innsikter hentet fra
by Chenhui Deng... klokken arxiv.org 03-05-2024
https://arxiv.org/pdf/2403.01232.pdfDypere Spørsmål