论文标题
与基于集的表示学习的对比二次分配
Contrasting quadratic assignments for set-based representation learning
论文作者
论文摘要
对比学习的标准方法是最大化数据不同观点之间的一致性。这些视图成对排序，使它们是正面的，编码与不同对象的视图相对应的同一对象的不同视图或负面的视图。监督信号来自最大程度地提高正面对的总相似性，而为了避免崩溃，需要负面对。在这项工作中，我们注意到，当从数据的视图中形成集合时，考虑单个对的方法无法解释内置和集合之间的相似性。因此，它限制了可用于训练表示形式的监督信号的信息内容。我们建议通过将对比对象作为集合进行对比，超越对比对象。为此，我们使用旨在评估集合和图形相似性的组合二次分配理论，并将设定对比度物镜作为对比度学习方法的正规化学方法。我们进行实验，并证明我们的方法改善了对公制学习和自学分类任务的学说。
The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects. The supervisory signal comes from maximizing the total similarity over positive pairs, while the negative pairs are needed to avoid collapse. In this work, we note that the approach of considering individual pairs cannot account for both intra-set and inter-set similarities when the sets are formed from the views of the data. It thus limits the information content of the supervisory signal available to train representations. We propose to go beyond contrasting individual pairs of objects by focusing on contrasting objects as sets. For this, we use combinatorial quadratic assignment theory designed to evaluate set and graph similarities and derive set-contrastive objective as a regularizer for contrastive learning methods. We conduct experiments and demonstrate that our method improves learned representations for the tasks of metric learning and self-supervised classification.
