Research map / Label-efficient and robust learning / Recognition and long-tail
Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes TDLSR, a theory-driven label-specific representation framework for incomplete multi-view multi-label learning where both features and labels may be missing.
Problem
Multi-view multi-label learning suffers from dual incompleteness: missing view features (due to storage limits) and missing labels (due to annotation cost), which degrades performance given heterogeneous features and many labels.
Approach
Builds label-specific representations guided by theoretical analysis to handle dual data incompleteness across heterogeneous views and numerous labels; the abstract is truncated so the exact mechanism is not stated.
Closest papers by meaning
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.92)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.91)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.90)
- View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning (CVPR 2024 · similarity 0.90)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.90)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.89)
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.