论文标题
对比度学习，多视图冗余和线性模型
Contrastive learning, multi-view redundancy, and linear models
论文作者
论文摘要
自我监督学习是一种基于创建人工监督的学习问题而无监督学习的经验成功方法。一种流行的自我监督方法是对比度学习，它利用了自然发生的相似和相似数据点的成对或相同数据的多种视图。这项工作提供了多视图设置中对比度学习的理论分析，每个基准都可以使用两个视图。主要的结果是，只要两个视图提供有关标签的冗余信息，学习表示表示的线性函数几乎是下游预测任务的最佳选择。
Self-supervised learning is an empirically successful approach to unsupervised learning based on creating artificial supervised learning problems. A popular self-supervised approach to representation learning is contrastive learning, which leverages naturally occurring pairs of similar and dissimilar data points, or multiple views of the same data. This work provides a theoretical analysis of contrastive learning in the multi-view setting, where two views of each datum are available. The main result is that linear functions of the learned representations are nearly optimal on downstream prediction tasks whenever the two views provide redundant information about the label.
