你的对比学习问题实际上是一个分布对齐问题
Your contrastive learning problem is secretly a distribution alignment problem
AI总结：
本文通过将对比学习重新定义为分布对齐问题，利用熵最优传输构建新损失函数，提升表征质量并支持定制化，为自监督学习提供新视角与工具。
摘要：
尽管对比学习（CL）在视觉和语言领域取得了成功，但其理论基础和构建表征的机制仍鲜为人知。在这项工作中，我们将对比学习中广泛使用的噪声对比估计损失与基于熵最优传输（OT）的分布对齐联系起来。这一联系使我们能够为现有的对比学习方法开发一系列不同的损失函数和多步迭代变体。直观上，通过利用潜在变量分布的更多信息，我们的方法能够对增强样本集内的关系进行更具分布感知的操作。我们提供了理论见解和实验证据，证明了我们的方法在“广义对比对齐”中的优势。通过这一框架，可以利用最优传输中的工具构建不平衡损失以处理噪声视图，并通过改变对齐约束来定制表征空间。通过将对比学习重新定义为对齐问题，并利用现有的最优传输优化工具，我们的工作为不同的自监督学习模型提供了新的见解和联系，此外还提供了更易于适应将领域知识融入学习的新工具。
英文摘要：
Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive estimation losses widely used in CL and distribution alignment with entropic optimal transport (OT). This connection allows us to develop a family of different losses and multistep iterative variants for existing CL methods. Intuitively, by using more information from the distribution of latents, our approach allows a more distribution-aware manipulation of the relationships within augmented sample sets. We provide theoretical insights and experimental evidence demonstrating the benefits of our approach for {\em generalized contrastive alignment}. Through this framework, it is possible to leverage tools in OT to build unbalanced losses to handle noisy views and customize the representation space by changing the constraints on alignment. By reframing contrastive learning as an alignment problem and leveraging existing optimization tools for OT, our work provides new insights and connections between different self-supervised learning models in addition to new tools that can be more easily adapted to incorporate domain knowledge into learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
