AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

Byung-Hoon Kim, Jong Chul Ye, Jae-Jin Kim

NeurIPS 2021 · Graph learning › Knowledge and temporal graphs · approach: Temporal graph neural architectures · 72 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
add orthogonal regularization (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 87.46 -> 88.20Improved
add spatial attention READOUT (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 86.55 -> 87.46Improved
add temporal attention Transformer encoder (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 85.64 -> 86.55Improved
add timestamp encoding to node features (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 82.34 -> 85.64Improved
use Schaefer 400 atlas instead of AAL (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 85.36 -> 88.20Improved
use Schaefer 400 atlas instead of Harvard-oxford (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 82.07 -> 88.20Improved
raise edge threshold from 30% to 40% (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 88.20 -> 89.02Improved
change window length from 50 to 25 (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 88.20 -> 85.45Hurt
replace SERO with TopKPooling scoring (ablation)STAGIN-SERO · HCP-Rest gender classificationaccuracy (%): 88.20 -> 77.02Hurt
use dynamic graph STAGIN-SERO instead of static GINGNN FC classifier · HCP-Rest gender classificationaccuracy (%): 81.34 -> 88.20Improved
use STAGIN-SERO instead of ST-GCNdynamic FC classifier · HCP-Task decodingaccuracy (%): 98.92 -> 99.19Improved
use dynamic FC instead of static FC graphsGNN FC classifier · HCP-Task decodingaccuracy (%): 93.87 -> 99.19Improved

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