自监督学习中最优数据增强的理论刻画
A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
AI总结：
本文利用核理论推导 VICReg、Barlow Twins 与 Spectral Contrastive Loss 下实现目标表示的最优数据增强，并给出构造算法，证明增强无需类似或多样且架构影响显著。
摘要：
数据增强在自监督学习（SSL）近期的成功中发挥着重要作用。尽管增强通常被理解为将不同视图之间的不变性编码到所学表示中，但这种解释忽视了预训练架构的影响，并暗示 SSL 需要与数据相似的多样化增强才能良好运行。然而，这些假设与经验证据并不一致，因此需要进一步的理论理解，以指导新领域中增强的有原则设计。为此，我们利用核理论推导了数据增强的解析表达式，使这些增强在预训练后能够获得所需的目标表示。我们考虑了非对比和对比损失，即 VICReg、Barlow Twins 和 Spectral Contrastive Loss，并提供了一种构造此类增强的算法。我们的分析表明，增强不必与数据相似才能学习有用表示，也不必具有多样性，并且架构对最优增强具有显著影响。
英文摘要：
Data augmentations play an important role in the recent success of self-supervised learning (SSL). While augmentations are commonly understood to encode invariances between different views into the learned representations, this interpretation overlooks the impact of the pretraining architecture and suggests that SSL would require diverse augmentations which resemble the data to work well. However, these assumptions do not align with empirical evidence, encouraging further theoretical understanding to guide the principled design of augmentations in new domains. To this end, we use kernel theory to derive analytical expressions for data augmentations that achieve desired target representations after pretraining. We consider non-contrastive and contrastive losses, namely VICReg, Barlow Twins and the Spectral Contrastive Loss, and provide an algorithm to construct such augmentations. Our analysis shows that augmentations need not be similar to the data to learn useful representations, nor be diverse, and that the architecture has a significant impact on the optimal augmentations.
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。
