AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature Selection

Yuzhou Liu, Jiarui Liu, Wanfu Gao

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Incomplete multi-view multi-label learning · 0 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 cross-view attention (ablation)RMAN-MMFS · SCENEAP: 0.257 -> 0.260Improved
add cross-view attention (ablation)RMAN-MMFS · MfeatAP: 0.830 -> 0.844Improved
add static redundancy penalty (ablation)RMAN-MMFS · OBJECTAP: 0.119 -> 0.128Improved
add static redundancy penalty (ablation)RMAN-MMFS · YeastAP: 0.314 -> 0.324Improved
add dynamic redundancy penalty (ablation)RMAN-MMFS · MfeatAP: 0.825 -> 0.844Improved
add dynamic redundancy penalty (ablation)RMAN-MMFS · YeastAP: 0.316 -> 0.324Improved
use correlation for static and MI for dynamic redundancy instead of other combinations (ablation)RMAN-MMFS · SCENECE: 13.934-13.996 -> 13.877Improved
use RMAN-MMFS instead of MLSMFSfeature selection · MfeatAP: 0.944 -> 0.844Hurt
use RMAN-MMFS instead of best baselinefeature selection · SCENEAP: 0.250 -> 0.260Improved
use RMAN-MMFS instead of best baseline, average over datasetsfeature selection · 6 datasets avgAP: 0.327 -> 0.331No clear effect

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