AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

PP-Brep: Few-Shot B-rep Classification with Hybrid Graph Representation

Jiacheng Hao, Chunying Liu, Hao Guo, Ruohan Wang, Hongping Gan, Yilei Shi

CVPR 2026 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering

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 local topology graph to node-only features (ablation)PP-Brep · FabWave-31 (1-shot)accuracy (%): 51.43 -> 57.08Improved
add global parallel graph (ablation)PP-Brep · FabWave-31 (1-shot)accuracy (%): 57.08 -> 60.95Improved
add regional association hypergraph (ablation)PP-Brep · FabWave-31 (1-shot)accuracy (%): 60.95 -> 72.89Improved
add RL-controlled adaptive perturbation to SimGRACE (ablation)contrastive pre-training · FabWave-31 (1-shot)accuracy (%): 67.50 -> 72.89Improved
use contrastive instead of generative pre-training (GraphMAE2) (ablation)pre-training · FabWave-31 (1-shot)accuracy (%): 45.76 -> 59.66 (GraphCL)Improved
use model-perturbation SimGRACE instead of graph-augmentation GraphCL (ablation)pre-training · FabWave-31 (1-shot)accuracy (%): 59.66 -> 67.50Improved
use structure-aware prompts instead of full fine-tuning (ablation)downstream tuning · FabWave-31 (1-shot)accuracy (%): 43.82 -> 72.89Improved
add structural context to prompt (SAP vs non-context prompt) (ablation)graph prompt · FabWave-31 (1-shot)accuracy (%): 70.30 -> 72.89Improved
add structural context to prompt on AUROC (ablation)graph prompt · FabWave-31 (1-shot)AUROC (%): 92.00 -> 91.53No clear effect
use in-place perturbation instead of full backbone duplication (ablation)contrastive pre-training · FabWave-31 (1-shot)accuracy (%): 72.39 -> 72.89No clear effect
use in-place perturbation instead of duplication (ablation)contrastive pre-training · DeepCAD, batch size 8192time per epoch (s): 1104.23 -> 19.31Improved
increase shots from 1 to 5PP-Brep · FabWave-31accuracy (%): 72.98 -> 87.55Improved

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