Research map / Architectures and efficiency / Attention and transformers
SAOT: An Enhanced Locality-Aware Spectral Transformer for Solving PDEs
Chenhong Zhou, Jie Chen, Zaifeng Yang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Wavelet attention in parallel to Fourier attention with gated fusion (spectral attention vs FA only) (ablation) | SAOT · Darcy | relative L2 error: 0.0058 -> 0.0049 | Improved |
| add Wavelet attention in parallel to Fourier attention with gated fusion (spectral attention vs FA only) (ablation) | SAOT · Elasticity | relative L2 error: 0.0232 -> 0.0080 | Improved |
| replace Fourier attention with Wavelet attention alone (ablation) | SAOT attention · Elasticity | relative L2 error: 0.0232 -> 0.0129 | Improved |
| replace Fourier attention with Wavelet attention alone (ablation) | SAOT attention · Darcy | relative L2 error: 0.0058 -> 0.0057 | No clear effect |
| fuse Wavelet attention with Fourier attention instead of WA alone (ablation) | SAOT attention · Elasticity | relative L2 error: 0.0129 -> 0.0080 | Improved |
| use spectral attention instead of AFNO token mixing (ablation) | SAOT · Elasticity | relative L2 error: 0.0228 -> 0.0080 | Improved |
| use spectral attention instead of GFNet token mixing despite fewer parameters (ablation) | SAOT · Darcy | relative L2 error: 0.0074 -> 0.0049 | Improved |
| use SAOT over Transolver | SAOT vs Transolver · Darcy | relative L2 error: 0.0058 -> 0.0049 | Improved |
| use SAOT over Transolver | SAOT vs Transolver · Navier-Stokes | relative L2 error: 0.0985 -> 0.0688 | Improved |
| use SAOT over Transolver | SAOT vs Transolver · Plasticity | relative L2 error: 0.0012 -> 0.0008 | Improved |
| use SAOT over Transolver | SAOT vs Transolver · Pipe | relative L2 error: 0.0043 -> 0.0063 | Hurt |
| use SAOT over Transolver | SAOT vs Transolver · Elasticity | relative L2 error: 0.0067 -> 0.0080 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GNOT — GNOT: A General Neural Operator Transformer for Operator Learning (ICML 2023) · better on 2 of 2 shared results
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
- Neural Operators with Localized Integral and Differential Kernels (ICML 2024 · similarity 0.87)
- Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains (ICML 2024 · similarity 0.87)
- Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains (NeurIPS 2025 · similarity 0.86)
- Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows (ICLR 2025 · similarity 0.86)
- Improved Operator Learning by Orthogonal Attention (ICML 2024 · similarity 0.86)
- Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning (ICML 2024 · similarity 0.86)
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.
