Current contrastive learning frameworks focus on leveraging a single
supervisory signal to learn representations, which limits the efficacy on
unseen data and downstream tasks. In this paper, we present a hierarchical
multi-label representation learning framework that can leverage all available
labels and preserve the hierarchical relationship between classes. We introduce
novel hierarchy preserving losses, which jointly apply a hierarchical penalty
to the contrastive loss, and enforce the hierarchy constraint. The loss
function is data driven and automatically adapts to arbitrary multi-label
structures. Experiments on several datasets show that our
relationship-preserving embedding performs well on a variety of tasks and
outperform the baseline supervised and self-supervised approaches. Code is
available at this https URL.

本文提出了一种层次化多标签表征学习框架，该框架可以利用所有可用标签并保留类别之间的层次关系，并引入新颖的层次保持损失。该方法是数据驱动的，自动适应任意多标签结构。实验表明，我们的关系保持嵌入在各种任务上表现良好，优于基线监督式和自监督式方法。