AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

PhysGNN: A Physics--Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image--Guided Neurosurgery

Yasmin Salehi, Dennis Giannacopoulos

NeurIPS 2022 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 6 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
Replace maximum aggregation with addition aggregation in two layers (ablation)PhysGNN with three GraphConv layers followed by three GraphSAGE layers · Dataset 2 validationMean Euclidean lossImproved
Replace maximum aggregation with addition aggregation in five layers (ablation)PhysGNN with three GraphConv layers followed by three GraphSAGE layers · Dataset 1 validationMean Euclidean lossNo clear effect
Use three GraphConv layers instead of one, replacing GraphSAGE layers consecutively (ablation)PhysGNN with the best-performing aggregation combination · Dataset 2 validationMean Euclidean lossImproved
Increase the number of GraphConv layers beyond the best-performing depth (ablation)PhysGNN · Datasets 1 and 2 validationMean Euclidean lossHurt

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