Research map / Label-efficient and robust learning / Recognition and long-tail
Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-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 a data-centric approach that prunes oversized candidate label sets in deep partial-label learning before training, to ease label disambiguation.
Problem
Deep partial-label learning becomes hard when candidate label sets are excessively large, since disambiguating the true label from many distractors degrades learning.
Approach
Shifts from learning-centric label disambiguation to a data-centric view: prune candidate label sets to remove unlikely labels before training, so that existing PLL training strategies operate on cleaner candidate sets.
Closest papers by meaning
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.91)
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.91)
- Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling (NeurIPS 2026 · similarity 0.90)
- Partial Label Learning with a Partner (AAAI 2024 · similarity 0.90)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Disentangled Partial Label Learning (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.