标题： 基于非线性依赖的自监督学习 显示英文标题

标题： Self-Supervised Learning Using Nonlinear Dependence

摘要： 自监督学习在当代应用中引起了广泛关注，尤其是在标记数据稀缺的情况下。虽然现有的自监督学习方法主要关注特征变化和线性相关性，但它们往往忽略了样本之间的复杂关系以及复杂数据中存在的非线性依赖关系。本文介绍了一种名为相关性-依赖性自监督学习（CDSSL）的新框架，该框架通过整合线性相关性和非线性依赖性，统一并扩展了现有的自监督学习范式，涵盖了样本间和特征间的交互作用。我们的方法采用了希尔伯特-施密特独立性准则（HSIC），以稳健地捕捉再生核希尔伯特空间中的非线性依赖关系，从而丰富表征学习。在多种基准数据集上的实验评估表明，CDSSL在提升表征质量方面具有显著效果。 显示英文摘要

摘要： Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the nonlinear dependencies inherent in complex data. In this paper, we introduce Correlation-Dependence Self-Supervised Learning (CDSSL), a novel framework that unifies and extends existing SSL paradigms by integrating both linear correlations and nonlinear dependencies, encapsulating sample-wise and feature-wise interactions. Our approach incorporates the Hilbert-Schmidt Independence Criterion (HSIC) to robustly capture nonlinear dependencies within a Reproducing Kernel Hilbert Space, enriching representation learning. Experimental evaluations on diverse benchmarks demonstrate the efficacy of CDSSL in improving representation quality.