SMT-DL: A Semi-Supervised Multi-Task Learning Framework Based on Dictionary Learning for Robust Feature Sharing

Bo Liu

doi:10.1016/j.neucom.2025.130996

SMT-DL: A Semi-Supervised Multi-Task Learning Framework Based on Dictionary Learning for Robust Feature Sharing

2025-07-14

0

PRE

AI

DOI：10.1016/j.neucom.2025.130996

Original

Original request for help

Save

Abstract

En 中文

• Proposed a semi-supervised multi-task learning (SMT-DL) method based on dictionary learning. • We establish a dual dictionary architecture by innovatively combining dictionary learning with a multi-task coordination mechanism. • We propose an optimization framework specific to the target equation. • The integration of multi-task information effectively promotes label propagation and enhances classification performance.

SMT-DL: A Semi-Supervised Multi-Task Learning Framework Based on Dictionary Learning for Robust Feature Sharing

Abstract

Journal

Organization