Prototype-Guided Memory Replay for Continual Learning

TL;DR

This paper introduces a memory-efficient continual learning method that uses prototype-guided memory replay within an online meta-learning framework to reduce forgetting and improve performance on text classification tasks.

Contribution

It proposes a novel dynamic prototype-guided memory replay module integrated into an online meta-learning model for continual learning.

Findings

Outperforms existing methods in reducing forgetting.

Requires fewer stored samples for effective learning.

Demonstrates robustness across different training set orders.

Abstract

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data distributions. Existing CL models often save a large number of old examples and stochastically revisit previously seen data to retain old knowledge. However, the occupied memory size keeps enlarging along with accumulating seen data. Hereby, we propose a memory-efficient CL method by storing a few samples to achieve good performance. We devise a dynamic prototype-guided memory replay module and incorporate it into an online meta-learning model. We conduct extensive experiments on text classification and investigate the effect of training set orders on CL model performance. The experimental results testify the superiority of our method in terms of forgetting mitigation and efficiency.