核心概念
Polynormer introduces a polynomial-expressive graph transformer with linear complexity, achieving state-of-the-art results on various graph datasets.
統計
Polynormer outperforms state-of-the-art GNN and GT baselines on most datasets.
Polynormer improves accuracy over baselines by up to 4.06% across 11 out of 13 node classification datasets.
Polynormer has linear complexity in regard to graph size, making it scalable to large graphs.
引用
"Polynormer adopts a linear local-to-global attention scheme to learn high-degree equivariant polynomials."
"Our extensive experiment results show that Polynormer outperforms state-of-the-art GNN and GT baselines on most datasets."