Partial label learning (PLL) is a typical weakly supervised learning framework, where each training instance is associated with a candidate label set, among which only one label is valid. To solve PLL problems, typically methods try to perform disambiguation for candidate sets by either using prior knowledge, such as structure information of training data, or refining model outputs in a self-training manner. Unfortunately, these methods often fail to obtain a favorable performance due to the lack of prior information or unreliable predictions in the early stage of model training. In this paper, we propose a novel framework for partial label learning with meta objective guided disambiguation (MoGD), which aims to recover the ground-truth label from candidate labels set by solving a meta objective on a small validation set. Specifically, to alleviate the negative impact of false positive labels, we re-weight each candidate label based on the meta loss on the validation set. Then, the classifier is trained by minimizing the weighted cross entropy loss. The proposed method can be easily implemented by using various deep networks with the ordinary SGD optimizer. Theoretically, we prove the convergence property of meta objective and derive the estimation error bounds of the proposed method. Extensive experiments on various benchmark datasets and real-world PLL datasets demonstrate that the proposed method can achieve competent performance when compared with the state-of-the-art methods.

翻译：部分标签学习（PLL）是一种典型的弱监督学习框架，其中每个训练实例关联一个候选标签集，且仅有一个标签是有效的。为解决PLL问题，典型方法通常通过利用先验知识（如训练数据的结构信息）或以自训练方式优化模型输出，对候选集进行消歧。然而，这些方法因缺乏先验信息或模型训练早期阶段预测不可靠，往往难以获得理想性能。本文提出一种基于元目标导向消歧（MoGD）的部分标签学习新框架，旨在通过在小验证集上求解元目标，从候选标签集中恢复真实标签。具体而言，为减轻误正标签的负面影响，我们根据验证集上的元损失对每个候选标签重新加权，随后通过最小化加权交叉熵损失训练分类器。该方法易于实现，可运用各类深度网络配合普通SGD优化器。理论上，我们证明了元目标的收敛性质，并推导了所提方法的估计误差界。在多种基准数据集和真实PLL数据集上的大量实验表明，与当前最优方法相比，本方法可获得具有竞争力的性能。