Addressing Catastrophic Forgetting in Few-Shot Problems

TL;DR

This paper introduces a Bayesian online meta-learning framework that effectively mitigates catastrophic forgetting in few-shot classification tasks, outperforming existing methods and enabling continual learning on sequential tasks.

Contribution

The paper proposes a novel Bayesian online meta-learning approach using Laplace approximation and variational inference to address catastrophic forgetting in few-shot learning.

Findings

Framework outperforms baselines in experiments

Capable of continual meta-learning on sequential tasks

Effectively mitigates catastrophic forgetting in few-shot scenarios

Abstract

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome catastrophic forgetting in few-shot classification problems. We demonstrate that the popular gradient-based model-agnostic meta-learning algorithm (MAML) indeed suffers from catastrophic forgetting and introduce a Bayesian online meta-learning framework that tackles this problem. Our framework utilises Bayesian online learning and meta-learning along with Laplace approximation and variational inference to overcome catastrophic forgetting in few-shot classification problems. The experimental evaluations demonstrate that our framework can effectively achieve this goal in comparison with various baselines. As an additional utility, we also demonstrate empirically that our framework is capable of meta-learning on sequentially arriving few-shot tasks from a stationary task distribution.