AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

GNOT: A General Neural Operator Transformer for Operator Learning

Zhongkai Hao, Zhengyi Wang, Hang Su, Chengyang Ying, Yinpeng Dong, Songming Liu, Ze Cheng, Jian Song, Jun Zhu

ICML 2023 · Architectures and efficiency › Attention and transformers · approach: Transformer neural operators for PDEs · 35 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
Add self-attention after cross-attention (cross+self block) instead of cross+cross (ablation)GNOT attention block · NACA, Elasticity, NS2d-c (p)relative L2 error: NACA 3.52e-2 -> 7.57e-3; Elasticity 3.31e-2 -> 8.65e-3; NS2d-c p 1.50e-2 -> 7.41e-3Improved
Put self-attention before cross-attention (self+cross) instead of cross+self (ablation)GNOT attention block · NS2d-c (p)relative L2 error: 7.41e-3 -> 9.89e-2Hurt
Use 3 experts in geometric gating instead of 1 expert (ablation)GNOT · Heatrelative L2 error: 0.04212 -> 0.03695Improved
Use 8 or 16 experts instead of 3 (ablation)GNOT · Heatrelative L2 error: 0.03695 -> 0.04732 (8 experts)Hurt
Increase number of attention heads from 1 to 16 (with 1 expert) (ablation)GNOT · Heatrelative L2 error: 0.04131 (1 head) vs 0.04180 (4 heads) vs 0.03952 (16 heads)Mixed
Heterogeneous normalized linear attention with geometric gating (GNOT) vs baselines on NS2d-c, NACA, Inductor2dGNOT · NS2d-c, NACA, Inductor2drelative L2 error: e.g., NACA 1.38e-2 (Geo-FNO) -> 7.57e-3Improved
GNOT vs GK-Transformer on Darcy2d (uniform grid)GNOT · Darcy2drelative L2 error: 1.05e-2 vs 8.40e-3 (GK-Transformer)Hurt

Later papers that compared with this method

3 later accepted papers report GNOT as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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