A prominent technique for self-supervised representation learning has been to
contrast semantically similar and dissimilar pairs of samples. Without access
to labels, dissimilar (negative) points are typically taken to be randomly
sampled datapoints, implicitly accepting that these points may, in reality,
actually have the same label. Perhaps unsurprisingly, we observe that sampling
negative examples from truly different labels improves performance, in a
synthetic setting where labels are available. Motivated by this observation, we
develop a debiased contrastive objective that corrects for the sampling of
same-label datapoints, even without knowledge of the true labels. Empirically,
the proposed objective consistently outperforms the state-of-the-art for
representation learning in vision, language, and reinforcement learning
benchmarks. Theoretically, we establish generalization bounds for the
downstream classification task.

提出了一种能够在缺少真实标签情况下，通过对不同标签数据进行负采样，纠正样本中同标签数据的影响的去偏置对比损失函数，实验证明该函数在视觉、语言和强化学习领域的表示学习中均优于现有的方法，并建立了下游分类任务的泛化界限。