EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

TL;DR

EMO introduces an external memory mechanism to retain and utilize past task gradients, significantly improving convergence and performance in few-shot meta-learning scenarios.

Contribution

We propose EMO, a novel memory-augmented optimizer that enhances few-shot meta-learning by recalling past experiences, with proven convergence and broad applicability.

Findings

EMO accelerates convergence in few-shot learning tasks.

EMO improves accuracy across multiple benchmarks.

EMO is compatible with various meta-learning models.

Abstract

Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is inspired by the human ability to recall past learning experiences from the brain's memory. EMO retains the gradient history of past experienced tasks in external memory, enabling few-shot learning in a memory-augmented way. By learning to retain and recall the learning process of past training tasks, EMO nudges parameter updates in the right direction, even when the gradients provided by a limited number of examples are uninformative. We prove theoretically that our algorithm converges for smooth, strongly convex objectives. EMO is generic, flexible, and model-agnostic, making it a simple plug-and-play optimizer that can be seamlessly embedded into existing optimization-based few-shot meta-learning approaches. Empirical results show that EMO scales well with most few-shot classification benchmarks and improves the performance of optimization-based meta-learning methods, resulting in accelerated convergence.