Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works. In this paper, we prove that contrastive learning with the standard InfoNCE loss is equivalent to spectral clustering on the similarity graph. Using this equivalence as the building block, we extend our analysis to the CLIP model and rigorously characterize how similar multi-modal objects are embedded together. Motivated by our theoretical insights, we introduce the kernel mixture loss, incorporating novel kernel functions that outperform the standard Gaussian kernel on several vision datasets.

翻译：对比学习是一种强大的自监督学习方法，但我们对它的工作原理及有效性原因的理论理解仍十分有限。本文证明，采用标准InfoNCE损失的对比学习等价于在相似图上进行谱聚类。基于这一等价关系，我们将分析扩展至CLIP模型，并严格刻画了多模态对象如何通过嵌入实现相似性对齐。受理论洞察启发，我们提出了核混合损失函数，该函数引入了新型核函数，在多个视觉数据集上的表现优于标准高斯核。