Few-Shot Learning Through an Information Retrieval Lens

TL;DR

This paper introduces an information retrieval-inspired method for few-shot learning that maximizes information extraction from limited data by optimizing relative orderings within training batches, leading to strong classification and retrieval performance.

Contribution

It proposes a novel training objective based on structured prediction and ranking optimization, enhancing few-shot learning by leveraging all available information in each batch.

Findings

Achieves state-of-the-art results on few-shot classification benchmarks.

Capable of effective few-shot retrieval tasks.

Introduces a ranking-based training framework for low-data regimes.

Abstract

Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available information in this low-data regime. We define a training objective that aims to extract as much information as possible from each training batch by effectively optimizing over all relative orderings of the batch points simultaneously. In particular, we view each batch point as a `query' that ranks the remaining ones based on its predicted relevance to them and we define a model within the framework of structured prediction to optimize mean Average Precision over these rankings. Our method achieves impressive results on the standard few-shot classification benchmarks while is also capable of few-shot retrieval.