论文标题
从因果的角度重新审视几乎没有学习的学习
Revisiting Few-Shot Learning from a Causal Perspective
论文作者
论文摘要
$ n $ -way $ k $ -shot Scheme是机器学习中的一个开放挑战。已经提出了许多基于公制的方法来解决此问题，例如匹配网络和剪辑适配器。尽管这些方法已经显示出很大的进步，但这些方法成功的机制尚未得到很好的探索。在本文中，我们试图通过因果机制来解释这些基于指标的几次学习方法。我们表明，现有方法可以看作是前门调整的特定形式，可以减轻虚假相关的影响，从而学习因果关系。这种因果解释可以为我们提供一个新的观点，以更好地理解这些现有的基于指标的方法。此外，基于这种因果解释，我们简单地引入了两种基于公制的少量学习的因果方法，这些方法不仅考虑了示例之间的关系，还考虑了表示的多样性。实验结果证明了我们在各种基准数据集上进行的几个射击分类中提出的方法的优越性。代码可在https://github.com/lingl1024/causalfewshot中找到。
Few-shot learning with $N$-way $K$-shot scheme is an open challenge in machine learning. Many metric-based approaches have been proposed to tackle this problem, e.g., the Matching Networks and CLIP-Adapter. Despite that these approaches have shown significant progress, the mechanism of why these methods succeed has not been well explored. In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism. We show that the existing approaches can be viewed as specific forms of front-door adjustment, which can alleviate the effect of spurious correlations and thus learn the causality. This causal interpretation could provide us a new perspective to better understand these existing metric-based methods. Further, based on this causal interpretation, we simply introduce two causal methods for metric-based few-shot learning, which considers not only the relationship between examples but also the diversity of representations. Experimental results demonstrate the superiority of our proposed methods in few-shot classification on various benchmark datasets. Code is available in https://github.com/lingl1024/causalFewShot.
