This paper studies a new problem, \emph{active learning with partial labels} (ALPL). In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process. To address ALPL, we first build an intuitive baseline that can be seamlessly incorporated into existing AL frameworks. Though effective, this baseline is still susceptible to the \emph{overfitting}, and falls short of the representative partial-label-based samples during the query process. Drawing inspiration from human inference in cognitive science, where accurate inferences can be explicitly derived from \emph{counter-examples} (CEs), our objective is to leverage this human-like learning pattern to tackle the \emph{overfitting} while enhancing the process of selecting representative samples in ALPL. Specifically, we construct CEs by reversing the partial labels for each instance, and then we propose a simple but effective WorseNet to directly learn from this complementary pattern. By leveraging the distribution gap between WorseNet and the predictor, this adversarial evaluation manner could enhance both the performance of the predictor itself and the sample selection process, allowing the predictor to capture more accurate patterns in the data. Experimental results on five real-world datasets and four benchmark datasets show that our proposed method achieves comprehensive improvements over ten representative AL frameworks, highlighting the superiority of WorseNet. The source code will be available at \url{https://github.com/Ferenas/APLL}.

翻译：本文研究了一个新问题——部分标签主动学习（ALPL）。在此设定中，标注者使用部分标签对查询样本进行标注，从而减轻了标注者进行精确标注的负担。为解决ALPL问题，我们首先构建了一个直观的基线方法，该方法可无缝融入现有主动学习框架。尽管该方法有效，但仍易受过拟合影响，且在查询过程中缺乏代表性的基于部分标签的样本。受认知科学中人类推理的启发——人类能够通过反例明确推导出精确推理——我们的目标是利用这种类人学习模式来应对过拟合问题，同时增强ALPL中选择代表性样本的过程。具体而言，我们通过反转每个实例的部分标签来构建反例，并提出一种简单而有效的WorseNet来直接学习这种互补模式。通过利用WorseNet与预测器之间的分布差距，这种对抗性评估方式能够同时提升预测器本身的性能和样本选择过程，使预测器能够捕捉数据中更精确的模式。在五个真实数据集和四个基准数据集上的实验结果表明，我们提出的方法在十个代表性主动学习框架上实现了全面改进，凸显了WorseNet的优越性。源代码将在\url{https://github.com/Ferenas/APLL}上提供。