Revisiting Few-Shot Learning from a Causal Perspective
This work offers a novel causal interpretation for few-shot learning, which could help researchers better understand and improve existing methods, though it is incremental in building on prior metric-based approaches.
The paper tackles the challenge of interpreting metric-based few-shot learning methods by providing a causal perspective, showing that existing approaches can be viewed as forms of front-door adjustment to reduce spurious correlations, and introduces two new causal methods that improve few-shot classification performance on benchmark datasets.
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.