Research map / Label-efficient and robust learning / Recognition and long-tail
Identifying Useful Learnwares for Heterogeneous Label Spaces
Lan-Zhe Guo, Zhi Zhou, Yu-Feng Li, Zhi-Hua Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| class-wise specification and class-wise identification (vs. RKME-basic) | learnware identification · Homogeneous and heterogeneous label spaces, Pre@k | Pre@1: e.g. 95.15 vs 54.54 (direct use); 59.09 vs 36.36 (heterogeneous) | Improved |
| class-wise specification (vs. RKME-basic) for trained-model correlation | specification similarity ranking · 22 user tasks, Kendall's tau | Kendall tau: outperforms on 20 of 22 datasets | Improved |
| reuse small model selected via specification instead of fine-tuning generic big model DenseNet201 | model reuse on user tasks · 22 user tasks, average accuracy | accuracy: 43.54 vs 32.99 | Improved |
| class-wise specification selection vs. brute-force fine-tuning of all models | learnware identification cost · Timing | speedup: at least thousand-fold (fine-tuning ~48s vs similarity ~0.003s) | Improved |
Closest papers by meaning
- Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation (NeurIPS 2024 · similarity 0.92)
- Towards Making Learnware Specification and Market Evolvable (AAAI 2024 · similarity 0.90)
- Learnware Specification via Label-Aware Neural Embedding (AAAI 2025 · similarity 0.89)
- On the Ability of Developers' Training Data Preservation of Learnware (NeurIPS 2024 · similarity 0.88)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.82)
- Heterogeneous Label Shift: Theory and Algorithm (ICML 2025 · similarity 0.82)
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.
