AI Paper Atlas

Research map / Graph learning / GNN architectures

Equivariant Neural Operator Learning with Graphon Convolution

Chaoran Cheng, Jian Peng

NeurIPS 2023 · Graph learning › GNN architectures · approach: Spectral GNN design · 1 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 residual operator layer (vs no-res) (ablation)InfGCN · QM9 rotatedNMAE (%): 6.14 -> 4.73Improved
add residual operator layer (vs no-res) (ablation)InfGCN · QM9 unrotatedNMAE (%): 3.72 -> 0.93Improved
use channel-wise tensor product instead of fully-connected (ablation)InfGCN · QM9 rotatedNMAE (%): 4.95 -> 4.73Improved
use channel-wise tensor product instead of fully-connected (ablation)InfGCN · QM9 unrotatedNMAE (%): 1.36 -> 0.93Improved
channel-wise instead of fully-connected: parameter count (ablation)InfGCN · QM9NMAE (%): 17.42 -> 1.20Improved
raise max spherical degree from L=0 to L=7 (ablation)InfGCN · QM9 rotatedNMAE (%): 12.62 -> 4.73Improved
raise max spherical degree from L=0 to L=7 (ablation)InfGCN · QM9 unrotatedNMAE (%): 12.05 -> 0.93Improved
raise max spherical degree from L=4 to L=7 (ablation)InfGCN · QM9 rotatedNMAE (%): 4.77 -> 4.73No clear effect
raise max spherical degree from L=4 to L=7 (ablation)InfGCN · QM9 unrotatedNMAE (%): 1.08 -> 0.93No clear effect
raise max spherical degree from L=2 to L=3 (ablation)InfGCN · QM9 rotatedNMAE (%): 6.95 -> 4.86Improved
raise max spherical degree from L=1 to L=2 (ablation)InfGCN · QM9 unrotatedNMAE (%): 8.07 -> 4.65Improved
InfGCN vs second-best DeepDFT2 (graphon conv + residual)InfGCN · CubicNMAE (%): 10.37 -> 8.98Improved

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