AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph Network

Dongxun Jiang, Borui Jia, Yuxuan Wang, Dongdong Zhang

ICML 2026 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic 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 temporal dependency encoder to short-term state encoder (ablation)SLT-BFGN · ADHD-200AUC (%): 64.65 -> 68.58Improved
add brain function memory to STSE+TDE (ablation)SLT-BFGN · ADHD-200AUC (%): 68.58 -> 73.28Improved
add brain function memory to STSE+TDE (ablation)SLT-BFGN · OpenNeuro-ds002424AUC (%): 52.89 -> 46.62Hurt
add long-term GNN network and fusion to short-term branch (ablation)SLT-BFGN · OpenNeuro-ds002424AUC (%): 46.62 -> 82.13Improved
add temporal dependency encoder to full model (ablation)SLT-BFGN · ADHD-200AUC (%): 63.59 -> 74.53Improved
add brain function memory to full model (ablation)SLT-BFGN · ADHD-200AUC (%): 73.50 -> 74.53Improved
add brain function memory to full model (ablation)SLT-BFGN · OpenNeuro-ds002424AUC (%): 76.69 -> 82.13Improved
add feature fusion to short- and long-term branches (ablation)SLT-BFGN · OpenNeuro-ds002424ACC (%): 69.77 -> 78.18Improved
add feature fusion to short- and long-term branches (ablation)SLT-BFGN · ADHD-200ACC (%): 65.83 -> 68.62Improved
add temporal dependency encoder to STSE (ablation)SLT-BFGN · ADHD-200ACC (%): 65.69 -> 65.83No clear effect
shuffle temporal order of graph sequencesgraph sequences · ADHD-200 KKI subsetlag-1 autocorrelation: 0.276 to 0.384 -> -0.072 to -0.021Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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