河南科技大学学报（自然科学版）2026，Vol.47Issue(2)：1-10,10.DOI:10.15926/j.cnki.issn1672-6871.2026.02.001
面向不可靠偏标记学习的鲁棒学习框架
A Robust Learning Framework for Unreliable Partial-Label Learning
摘要
Abstract
To address the problem that candidate label sets may exclude the true label in unreliable partial-label learning,a robust learning framework with alternating optimization between the representation space and the label space was proposed.K-nearest neighbor relationships in the embedding space are exploited to refine candidate label sets and update dynamic label distributions.Meanwhile,prototype-based contrastive learning and consistency regularization guided by the dynamic label distributions are introduced to enhance the discriminability and robustness of feature representations,thereby facilitating the refinement of candidate label sets during the alternating optimization process.Extensive experiments conducted on both synthetic and real-world unreliable partial-label datasets demonstrate the effectiveness and stability of the proposed robust learning framework.关键词
偏标记学习/不可靠标注场景/鲁棒表示学习/标记修正/一致性正则化/标记消歧/对比学习Key words
partial-label learning/unreliable annotation scenarios/robust representation learning/label correction/consistency regularization/label disambiguation/contrastive learning分类
信息技术与安全科学引用本文复制引用
李昭仪,张柘,台宪青..面向不可靠偏标记学习的鲁棒学习框架[J].河南科技大学学报（自然科学版）,2026,47(2):1-10,10.基金项目
国家重点研发计划项目(2023YFB3904900) （2023YFB3904900）
江苏省前沿技术研发计划项目(BF2024027) （BF2024027）
