AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Brain Networks Should Be Learned, Not Constructed

Liang Yang, Shuai Zhai, Ziyi Ma, Jiaming Zhuo, Di Jin, Chuan Wang, Zhen Wang, Xiaochun Cao

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Brain and biological graph learning

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 HDM learnable brain network construction to GCN (ablation)GCN · ABIDEACC: 59.30 -> 63.34Improved
add HDM to GCN (ablation)GCN · ADHD-200ACC: 64.92 -> 70.02Improved
add HDM to BrainNETTF (ablation)BrainNETTF · ABIDEACC: 69.26 -> 71.61Improved
add HDM to BrainNETTF (ablation)BrainNETTF · ADHD-200ACC: 72.67 -> 76.19Improved
add HDM to BrainNETTF (ablation)BrainNETTF · ABIDEAUC: 77.93 -> 77.61No clear effect
add HDM to BQN (ablation)BQN · ABIDEACC: 72.53 -> 73.15No clear effect
add HDM to BQN (ablation)BQN · ABIDEAUC: 79.85 -> 77.59Hurt
add HDM to BQN (ablation)BQN · ADHD-200ACC: 75.68 -> 79.97Improved
add denoising module and normalization together (ablation)BRep · ABIDE and ADHD-200AUC: AUC reduced by 7.84% when both removedImproved
add learnable BRep construction over baseline NN (MLP)MLP · ADHD-200ACC: 70.68 -> 77.82Improved
BRep vs second-best BQN on ADHD-200 ACCBQN · ADHD-200ACC: 2.14% on ACCImproved

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