Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of these approaches aligns the covariance or correlation matrix with the identity matrix. Despite impressive performance across various downstream tasks, these methods often suffer from biased sample risk, leading to substantial optimization shifts in mini-batch settings and complicating theoretical analysis. In this paper, we introduce a novel \underline{\bf Adv}ersarial \underline{\bf S}elf-\underline{\bf S}upervised Representation \underline{\bf L}earning (Adv-SSL) for unbiased transfer learning with no additional cost compared to its biased counterparts. Our approach not only outperforms the existing methods across multiple benchmark datasets but is also supported by comprehensive end-to-end theoretical guarantees. Our analysis reveals that the minimax optimization in Adv-SSL encourages representations to form well-separated clusters in the embedding space, provided there is sufficient upstream unlabeled data. As a result, our method achieves strong classification performance even with limited downstream labels, shedding new light on few-shot learning.

翻译：从大量无标签数据中学习可迁移的数据表征仍然是机器学习的核心挑战。尽管已有众多自监督学习方法被提出以应对这一挑战，但其中一大类方法将协方差或相关矩阵与单位矩阵对齐。尽管在各种下游任务中表现出色，这些方法常受样本风险偏差的影响，导致在小批量设置中出现显著的优化偏移，并使理论分析复杂化。本文提出了一种新颖的\underline{\bf 对抗性自监督表征学习}（Adv-SSL）方法，在与其有偏差的同类方法相比无需额外成本的情况下，实现无偏差的迁移学习。我们的方法不仅在多个基准数据集上超越了现有方法，还得到了全面的端到端理论保证的支持。分析表明，只要存在充足的上游无标签数据，Adv-SSL中的极小极大优化会促使表征在嵌入空间中形成良好分离的聚类。因此，即使在下游标签有限的情况下，我们的方法也能实现强大的分类性能，为少样本学习提供了新的启示。