In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLE

翻译：在这项工作中，我们聚焦于标签增强这一具有挑战性的问题，其目标是从逻辑标签中精确恢复标签分布，并提出了一种新颖的标签信息瓶颈方法用于标签增强。在标签分布的恢复过程中，数据集中包含的标签无关信息可能导致恢复性能不佳。为解决这一局限，我们致力于挖掘关键的标签相关信息以提升恢复性能。我们的方法将标签增强问题表述为以下两个联合过程：1）学习包含关键标签相关信息的表示；2）基于所学表示恢复标签分布。标签相关信息可通过所学表示形成的"瓶颈"被挖掘。值得注意的是，我们的方法既能探索关于标签分配的相关信息，也能探索关于标签差距的相关信息。在多个基准标签分布学习数据集上进行的评估实验验证了LIB的有效性和竞争力。我们的源代码可在https://github.com/qinghai-zheng/LIBLE获取。