AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learnable Pooling in Graph Convolutional Networks for Brain Surface Analysis

Karthik Kuduva Gopinath, Christian Desrosiers, Hervé Lombaert

TPAMI 2020 · Graph learning › Graph self-supervised learning · approach: Brain and biological graph learning · 31 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 global average pooling with learnable pooling (ablation)graph convolution network · Mindboggle sex classificationaccuracy: 60.76 -> 81.33Improved
replace fixed atlas parcellation pooling with learnable pooling (ablation)graph convolution network · Mindboggle sex classificationaccuracy: 64.59 -> 81.33Improved
replace unsupervised spectral clustering pooling with learned supervised clusters (ablation)graph convolution network · Mindboggle sex classificationaccuracy: 67.94 -> 81.33Improved
train on 100-node sub-sampled graphs instead of full graphs (ablation)learnable pooling · Mindboggle sex classificationaccuracy: 84.21 -> 55.02Hurt
train on 50K-node sub-sampled graphs instead of full graphs (ablation)learnable pooling · Mindboggle sex classificationaccuracy: 84.21 -> 81.33Mixed
test 50K-node-trained model on full graphs (ablation)learnable pooling · Mindboggle sex classificationaccuracy: 81.33 -> 78.94Mixed
add spectral node coordinates as input (ablation)graph convolution network · ADNI NC vs MCIaccuracy: 63.71 -> 70.79Improved
add spectral node coordinates as input (ablation)graph convolution network · ADNI NC vs ADaccuracy: 76.00 -> 89.33Improved
add spectral node coordinates as input (ablation)graph convolution network · ADNI MCI vs ADaccuracy: 74.03 -> 76.92Improved
give raw (x,y,z) mesh coordinates instead of spectral coordinates (ablation)graph convolution network · ADNI classificationaccuracyHurt
replace random forest on cortical features with learnable-pooling GCNrandom forest (cortical-based) · ADNI NC vs ADaccuracy: 80 -> 89.33Improved
replace random forest on cortical features with learnable-pooling GCNrandom forest (cortical-based) · ADNI MCI vs ADaccuracy: 65 -> 76.92Improved

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