Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of downstream tasks under Conditional Independence (CI) condition. However, the downstream sample complexity gets much worse if the CI condition does not hold. One interesting question is whether we can make the CI condition hold by using downstream data to refine the unlabeled data to boost self-supervised learning. At first glance, one might think that seeing downstream data in advance would always boost the downstream performance. However, we show that it is not intuitively true and point out that in some cases, it hurts the final performance instead. In particular, we prove both model-free and model-dependent lower bounds of the number of downstream samples used for data refinement. Moreover, we conduct various experiments on both synthetic and real-world datasets to verify our theoretical results.
翻译:以文字为基础的自我监督的学习通过手工制作的借口任务,对未贴标签的数据学习语义表达方式,然后对下游任务使用所学的代言方式,这有效地降低了在有条件独立条件下下游任务的抽样复杂性。然而,如果光学独立条件不起作用,下游样本的复杂性就会大为恶化。一个令人感兴趣的问题是,我们是否能够通过使用下游数据改进未贴标签的数据来维持CI的条件,以促进自我监督的学习。乍一看,人们可能会认为,提前看到下游数据将总是会提高下游的性能。然而,我们表明,这并非直觉真实,并指出,在某些情况下,它会损害最后的性能。特别是,我们证明,在用于改进数据的下游样本数量方面,没有模型,而且模式依赖较低界限。此外,我们还在合成和现实世界数据集进行各种实验,以核实我们的理论结果。