Research map / Label-efficient and robust learning / Recognition and long-tail
Two-Stage Label Embedding via Neural Factorization Machine for Multi-Label Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| use TSLE instead of best baseline on Emotions | multi-label classifiers · Emotions | Micro-F1: 0.6585 -> 0.6933 | Helped |
| use TSLE instead of best baseline on Yeast | multi-label classifiers · Yeast | Micro-F1: 0.6262 -> 0.5908 | Hurt |
| use TSLE instead of best baseline on NUS-WIDE | multi-label classifiers · NUS-WIDE | Macro-F1: 0.0694 -> 0.0522 | Hurt |
| use TSLE instead of LM-kNN (kernelized FM encoding plus DNN) | LM-kNN · Eurlex dc | Micro-F1: 0.9206 -> 0.9492 | Helped |
| use TSLE instead of LM-kNN on Eurlex desc | LM-kNN · Eurlex desc | Example-F1: 0.7101 -> 0.7006 | Mixed |
| model label correlations (LM-kNN/TSLE) instead of independent binary relevance | BR · multi-label datasets | F1 | Helped |
| vary learning rate and loss leverage parameter alpha (ablation) | TSLE · four datasets | Micro-F1 / Macro-F1 | No clear effect |
Closest papers by meaning
- Learning Deep Latent Space for Multi-Label Classification (AAAI 2017 · similarity 0.89)
- Modeling Label Space Interactions in Multi-label Classification using Box Embeddings (ICLR 2022 · similarity 0.89)
- Incorporating Label Embedding and Feature Augmentation for Multi-Dimensional Classification (AAAI 2020 · similarity 0.87)
- Neural Collapse in Multi-label Learning with Pick-all-label Loss (ICML 2024 · similarity 0.86)
- Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification (AAAI 2024 · similarity 0.85)
- Generalization Analysis for Multi-Label Learning (ICML 2024 · similarity 0.85)
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.