AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection

Ling Zhan, Zhen Li, Junjie Huang, Tao Jia

ICLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 1 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
use structure-aware attention-based SPS instead of naive attention averaging (MHA) (ablation)SCLCS · brain fingerprinting, ratio 0.1nDCG@5: 1.32 -> 81.21Improved
use structure-aware attention-based SPS instead of naive attention averaging (MHA) (ablation)SCLCS-Dense · MDD diagnosis, ratio 0.5nDCG@5: 27.45 -> 81.87Improved
add density-balanced sampling to SCLCS (ablation)SCLCS · MDD diagnosis, ratio 0.5nDCG@5: 64.18 -> 81.87Improved
add density-balanced sampling to SCLCS (ablation)SCLCS · MDD diagnosis, ratio 0.1nDCG@5: 48.38 -> 57.29Improved
add density-balanced sampling to SCLCS (ablation)SCLCS · brain fingerprinting, ratio 0.3nDCG@5: 50.24 -> 79.18Improved
add density-balanced sampling to SCLCS (ablation)SCLCS · brain fingerprinting, ratio 0.1nDCG@5: 81.21 -> 35.73Hurt
add density-balanced sampling to SCLCS (ablation)SCLCS · brain fingerprinting, ratio 0.5nDCG@5: 72.68 -> 51.54Hurt
use SCLCS instead of Random selection (ablation)Core-set selection · brain fingerprinting, ratio 0.1nDCG@5: 15.17 -> 81.21Improved
use SCLCS instead of Random selection (ablation)Core-set selection · brain fingerprinting, ratio 0.3nDCG@5: 69.57 -> 50.24Hurt
use SCLCS-Dense instead of best baseline BOSS (ablation)Core-set selection · MDD diagnosis, ratio 0.5nDCG@10: 84.70 -> 86.25Improved
use SCLCS-Dense instead of Random selection (ablation)Core-set selection · MDD diagnosis, ratio 0.3nDCG@5: 23.77 -> 74.62Improved

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