Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

TL;DR

Meta Navigator introduces an automated framework that searches for optimal adaptation policies in few-shot learning, outperforming existing methods across multiple benchmarks by leveraging a differentiable search strategy.

Contribution

The paper proposes a novel AutoML-inspired framework for automating the selection of adaptation policies in few-shot learning, covering a broad search space and using gradient-based optimization.

Findings

Significantly outperforms baseline methods on benchmark datasets.

Demonstrates the effectiveness of automated policy search in few-shot learning.

Supports gradient-based optimization for efficient search.

Abstract

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios. It is therefore tricky to decide which learning strategies to use under different task conditions. Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs. The goal of our work is to search for good parameter adaptation policies that are applied to different stages in the network for few-shot classification. We present a search space that covers many popular few-shot learning algorithms in the literature and develop a differentiable searching and decoding algorithm based on meta-learning that supports gradient-based optimization. We demonstrate the effectiveness of our searching-based method on multiple benchmark datasets. Extensive experiments show that our approach significantly outperforms baselines and demonstrates performance advantages over many state-of-the-art methods. Code and models will be made publicly available.