SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.13816 · 2022

Revisiting Few-Shot Learning from a Causal Perspective

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.13816")
get_code_for_paper("2209.13816")
have("2209.13816")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2209.13816.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2209.13816.svg)](https://syntology.ai/paper/2209.13816)

Connect an agent — have() is free.