arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.16482cs.LG
收藏

基于相似性提示的确定性多标签学习

Determined Multi-Label Learning via Similarity-Based Prompt

China University of Mining and Technology(中国矿业大学)

Meng Wei, Zhongnian Li, Peng Ying, Yong Zhou, Xinzheng Xu

AI总结:

提出DMLL标注设置以降低多标签分类的标注成本,通过风险一致估计器与基于相似性的提示学习方法,从确定性标注数据中有效学习多标签分类器,性能优于现有方法。

摘要:

在多标签分类中,每个训练实例同时与多个类别标签相关联。然而,在实际应用中,为每个训练实例收集完全准确的类别标签既耗时又费力。为了缓解这一问题,提出了一种名为Determined Multi-Label Learning(DMLL,确定性多标签学习)的新型标注设置,旨在有效减轻多标签任务中固有的标注成本。在这种新型标注设置中,每个训练实例与一个确定性标签(“Yes”或“No”)相关联,指示该训练实例是否包含所提供的类别标签。所提供的类别标签从整个候选标签集中随机均匀地选择。此外,每个训练实例只需被确定一次,这显著降低了多标签数据集标注任务的标注成本。本文从理论上推导出一个风险一致估计器,用于从这些确定性标注的训练数据中学习多标签分类器。此外,我们首次引入了一种基于相似性的提示学习方法,通过最小化大规模预训练模型的风险一致损失,学习具有更丰富语义信息的补充提示。广泛的实验验证了该方法的有效性,表现出与现有最先进方法相比更优越的性能。

英文摘要:

In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each training instance is time- and labor-consuming for real-world applications. To alleviate this problem, a novel labeling setting termed \textit{Determined Multi-Label Learning} (DMLL) is proposed, aiming to effectively alleviate the labeling cost inherent in multi-label tasks. In this novel labeling setting, each training instance is associated with a \textit{determined label} (either "Yes" or "No"), which indicates whether the training instance contains the provided class label. The provided class label is randomly and uniformly selected from the whole candidate labels set. Besides, each training instance only need to be determined once, which significantly reduce the annotation cost of the labeling task for multi-label datasets. In this paper, we theoretically derive an risk-consistent estimator to learn a multi-label classifier from these determined-labeled training data. Additionally, we introduce a similarity-based prompt learning method for the first time, which minimizes the risk-consistent loss of large-scale pre-trained models to learn a supplemental prompt with richer semantic information. Extensive experimental validation underscores the efficacy of our approach, demonstrating superior performance compared to existing state-of-the-art methods.

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。

↑