arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2505.09354cs.LG
收藏

挖掘偏标签学习中干净样本的潜在监督信息

Exploiting the Potential Supervision Information of Clean Samples in Partial Label Learning

Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系);Department of Computer Science, Hong Kong Baptist University(香港 Baptist 大学计算机科学系)

Guangtai Wang, Chi-Man Vong, Jintao Huang

AI总结:

针对偏标签学习忽视数据集中干净样本强监督信息的问题,提出CleanSE校准策略,利用近邻干净标签增强候选置信度并约束标签计数,可广泛提升现有PLL方法性能。

摘要:

在偏标签学习(PLL)中,削弱假阳性标签的影响对于执行消歧至关重要。然而,现有消歧策略主要关注利用单个偏标签实例的特征,却忽视了随机存在于数据集中的干净样本所具有的强监督信息。在本工作中,我们表明可以收集干净样本以提供指导,并增强最可能候选标签的置信度。受可微计数损失策略和K-Nearest-Neighbor算法方式的启发,我们提出了一种名为CleanSE的新型校准策略。具体而言,在如下假设下,我们将更高的重要性赋予最可靠的候选标签:对于每个干净样本,如果其标签是其在表示空间中最近邻的候选标签之一,那么该标签更有可能是其邻居的真实标签。此外,干净样本通过将每个标签的标签数量限制在特定区间内,有助于刻画样本分布。在3个合成基准和5个真实世界PLL数据集上的大量实验表明,该校准策略可应用于大多数最先进的PLL方法,并提升它们的性能。

英文摘要:

Diminishing the impact of false-positive labels is critical for conducting disambiguation in partial label learning. However, the existing disambiguation strategies mainly focus on exploiting the characteristics of individual partial label instances while neglecting the strong supervision information of clean samples randomly lying in the datasets. In this work, we show that clean samples can be collected to offer guidance and enhance the confidence of the most possible candidates. Motivated by the manner of the differentiable count loss strat- egy and the K-Nearest-Neighbor algorithm, we proposed a new calibration strategy called CleanSE. Specifically, we attribute the most reliable candidates with higher significance under the assumption that for each clean sample, if its label is one of the candidates of its nearest neighbor in the representation space, it is more likely to be the ground truth of its neighbor. Moreover, clean samples offer help in characterizing the sample distributions by restricting the label counts of each label to a specific interval. Extensive experiments on 3 synthetic benchmarks and 5 real-world PLL datasets showed this calibration strategy can be applied to most of the state-of-the-art PLL methods as well as enhance their performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑