Task Affinity with Maximum Bipartite Matching in Few-Shot Learning

TL;DR

This paper introduces a novel asymmetric affinity score based on maximum bipartite matching and Fisher Information to improve few-shot learning by identifying relevant training data for test tasks.

Contribution

It proposes a new affinity score and algorithm that enhance few-shot learning by effectively selecting relevant data, outperforming existing methods on benchmark datasets.

Findings

Improved classification accuracy over state-of-the-art methods.

Effective data relevance identification for few-shot tasks.

Works well even with smaller models.

Abstract

We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartite matching algorithm and utilizes the Fisher Information matrix. We provide theoretical analyses demonstrating that the proposed score is mathematically well-defined, and subsequently use the affinity score to propose a novel algorithm for the few-shot learning problem. In particular, using this score, we find relevant training data labels to the test data and leverage the discovered relevant data for episodically fine-tuning a few-shot model. Results on various few-shot benchmark datasets demonstrate the efficacy of the proposed approach by improving the classification accuracy over the state-of-the-art methods even when using smaller models.