Research map / Label-efficient and robust learning / Recognition and long-tail
Provably Consistent Partial-Label Learning
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 RC rather than CC with a neural-network base model | Partial-label learning · MNIST, Kuzushiji-MNIST, Fashion-MNIST, and CIFAR-10 | accuracy: 97.87$\pm$0.10\% -> 98.00$\pm$0.11\%; 88.83$\pm$0.40\% -> 89.38$\pm$0.28\%; 87.88$\pm$0.25\% -> 88.38$\pm$0.16\%; 75.78$ | Helped |
| Use RC rather than CC with a linear model | Partial-label learning · UCI and real-world partially labeled datasets | accuracy | Mixed |
| Generate candidate-label sets with higher entropy, matching the proposed generation model more closely | RC and CC · MNIST, Kuzushiji-MNIST, Fashion-MNIST | accuracy: MLP MNIST RC: 95.29 -> 98.00; MLP KMNIST RC: 79.88 -> 89.38; MLP FMNIST RC: 79.78 -> 88.38 | Helped |
| Use the Case 1 generation model, which matches the proposed model less well | RC and CC · Benchmark datasets | accuracy: MLP MNIST RC: 98.00 -> 95.29; MLP KMNIST RC: 89.38 -> 79.88; MLP FMNIST RC: 88.38 -> 79.78 | Hurt |
Closest papers by meaning
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.92)
- Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (AAAI 2024 · similarity 0.91)
- What Makes Partial-Label Learning Algorithms Effective? (NeurIPS 2024 · similarity 0.91)
- Conformal Prediction for Partial Label Learning (AAAI 2025 · similarity 0.89)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.89)
- Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning (ICML 2025 · 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.